Round 16 reviewer aggregate (logs/review_round16_aggregate.md):
P1 fixes:
- routes/models.py /delete-cached llama guard pairs loading_id with
loading_hf_variant so deleting a different cached quant (Q8_0)
while another variant (Q4_K_M) is loading is no longer blocked.
- core/inference/diffusion.py load_model now calls
_release_other_gpu_owners_for_diffusion BEFORE
_release_chat_backend_for_diffusion. The other-owners helper
RAISES on active training/export, so a route -> worker race or
direct backend caller no longer drops the user's chat model
before the diffusion load is refused.
- routes/models.py /delete-cached diffusion guard fails CLOSED
(503) on HF cache scan failure instead of silently falling
through to repo-id-only matching, which could miss a loaded
local snapshot path.
- routes/inference.py _release_llama_for and
_release_safetensors_chat_for now raise 503 on actual unload
failure (exception or False return), so new GPU workloads do
not start while the old chat process still owns VRAM.
- core/inference/diffusion.py status() now takes
include_internal=False by default and only exposes the
guard-facing active_*/pending_* paths when callers opt in. The
public /api/inference/images/status route gets the redacted
payload; routes/models.py delete guards pass
include_internal=True so they still see the raw paths.
- core/inference/diffusion.py generate_image_with_metadata routes
the response model through _display_repo_id so /images/generate
cannot echo back an absolute local path.
P2 fixes:
- routes/inference.py /images/load now maps backend "Could not
verify training/export status" to 503 instead of 409, matching
the route-level pre-check.
- core/inference/diffusion.py _release_other_gpu_owners_for_diffusion
raises "Could not verify export status" when the
is_export_active() probe itself raises, instead of silently
treating it as active export.
- core/inference/diffusion.py detect_family compares compact family
spellings (Flux2Klein) against per-token compact strings so
unsloth/Flux2Klein-GGUF matches the flux.2-klein family without
matching the embedded substring inside flux.20.
- main.py installs a RequestValidationError handler that scrubs
hf_xxxxx tokens out of the 422 response body so a rejected
``repo_id`` containing a URL-embedded HF token does not echo it
back to the browser.
Tests:
- 3 new regression cases (Flux2Klein compact alias, public status
redaction, generate_image_with_metadata redaction).
- All 75 diffusion backend + route tests pass.
Round 15 reviewer aggregate (logs/review_round15_aggregate.md):
P1 fixes:
- core/inference/llama_cpp.py publishes loading_model_identifier +
loading_hf_variant AFTER acquiring _serial_load_lock; previously
a queued second load could overwrite or clear the identifier
currently in flight, breaking delete-safety and GPU handoff guards.
- routes/models.py /delete-finetuned compares the pending llama
load against loading_hf_variant (new), not the stale hf_variant
from the previous loaded model. Without this, a Q4-loaded
directory loading Q8 would still accept a Q8 delete.
- core/inference/diffusion.py _release_other_gpu_owners_for_diffusion
now also raises when training is active so direct backend callers
cannot bypass the route layer's 409 guard. Mirrors the
export-active check the same helper already enforces.
- routes/models.py /delete-cached diffusion guard compares owned
diffusion paths against the HF cache root for the target repo
via _all_hf_cache_scans + _is_path_under. Without this, loading
from a local models--owner--model/snapshots/<sha> path let the
cache delete proceed while the snapshot was still mmap'd.
- models/inference.py DiffusionLoadRequest refuses URL-embedded
hf_xxxxx tokens in repo_id / base_repo at the API boundary, so
the value never reaches self._repo_id and status() can never
echo it back to other authenticated sessions.
P2 fixes:
- core/inference/diffusion.py status() routes UI-facing repo_id /
base_repo through _display_repo_id, which collapses absolute
local paths to the leaf name (delete guards still see the full
path via active_*/pending_*).
- routes/inference.py /images/load maps backend RuntimeError that
reports an export/training conflict to HTTP 409 instead of 400.
- core/inference/diffusion.py detect_family now uses token-boundary
matching so owner/flux.20-model does not collide with flux.2.
P3 fixes:
- tests/test_diffusion_routes.py drops the partial routes.inference
module from sys.modules if exec_module() raises, so the real
ImportError surfaces instead of a misleading AttributeError on
follow-up tests.
Tests:
- 5 new regression cases (display_repo_id, token-boundary family
detection, training-active raise from backend helper, embedded HF
token rejection).
- All 72 diffusion backend + route tests pass.
Round 14 reviewer aggregate (logs/review_round14_aggregate.md):
P1 fixes:
- routes/export.py /load-checkpoint now runs the active-export 409
guard BEFORE the chat / diffusion unloads, so a rejected request
no longer tears down unrelated GPU state.
- core/inference/llama_cpp.py wraps the WHOLE load_model body in a
single try/finally that publishes loading_model_identifier across
download, metadata read, VRAM settle, process spawn, and health
check. Done via a thin load_model wrapper around the existing
body (renamed _load_model_impl) to avoid reindenting hundreds of
lines.
- routes/models.py /delete-finetuned now checks
loading_model_identifier so a pending HF GGUF download cannot
have its destination directory rmtree'd before llama-server
spawns.
- core/inference/diffusion.py stores the original caller-supplied
gguf_filename (e.g. ``BF16/model.gguf``) in a new self._gguf_filename
field and exposes it as active_gguf_filename. UI-facing
gguf_filename still collapses to basename for the panel.
- routes/models.py /delete-cached llama guard now allows safe
different-variant deletes when hf_variant differs, matching the
diffusion path's variant-aware behaviour.
- core/inference/diffusion.py tracks self._cpu_offload_enabled and
forces a CPU torch.Generator when offload is on, so seeded
generation no longer crashes on CUDA hosts with the default offload
enabled.
P2 fixes:
- core/inference/diffusion.py detect_family normalises mixed
separators (``Qwen_Image-Edit-GGUF``, ``Qwen-Image_Edit-GGUF``,
``QwenImageEdit-GGUF``) so every Qwen-Image-Edit spelling is
excluded from the base Qwen-Image family.
- core/inference/diffusion.py logger.info / logger.error in
load_model run repo_id and effective_base through _redact_hf_tokens
so URL-embedded ``hf_xxxxx`` tokens never reach structured-log
sinks.
- core/inference/diffusion.py _release_other_gpu_owners_for_diffusion
now raises RuntimeError when an export job is active instead of
logging and continuing, so direct backend callers cannot bypass
the route layer's 409 guard.
- core/inference/diffusion.py full-diffusers repo / base_repo paths
expand ``~`` via _expand_existing_local_path so
``repo_id="~/models/my-flux"`` no longer falls through to the Hub.
Tests:
- 5 new regression cases (mixed Qwen-Image-Edit separators, token
redaction, status full-filename, CPU offload generator device,
staging Windows leaf already-set sanity).
- All 68 diffusion backend + route tests pass.
Round 13 follow-up: on Windows Path('/etc/passwd').is_absolute()
returns False because POSIX absolute paths read as drive-relative,
which let the traversal check fall through to resolve(strict=True)
and crash with a raw FileNotFoundError instead of the friendlier
RuntimeError. Add a PurePosixPath check + explicit leading-separator
guard and wrap the resolve() in try/except so a missing path inside
the chosen repo is reported as 'Local repo path does not contain ...'
on every OS.
Pre-existing 59 diffusion backend + route tests still pass; staging
Windows Diffusion CI was failing on this exact case.
Round 13 reviewer aggregate (logs/review_round13_aggregate.md):
P1 fixes:
- routes/export.py load_checkpoint refuses (409) when an export job
is currently active, mirroring the chat/diffusion/training handoff
guards. ``is_export_active`` absence is tolerated for older / mocked
backends.
- core/inference/diffusion.py local-path GGUF loader now accepts
relative directories (Studio exports surface as ``exports/my-flux``)
and confines ``gguf_filename`` to the chosen repo via
``_resolve_local_gguf_child``: absolute filenames, ``..`` segments,
and Windows separators are rejected before any file is opened.
- core/inference/diffusion.py status() exposes ``active_gguf_filename``
alongside the pending variant so delete guards can pair each owned
repo with the GGUF variant it actually owns.
- routes/models.py cache delete + finetuned delete adopt a shared
``_diffusion_owned_targets`` + ``_variant_delete_is_safe_for_owned_gguf``
helper. Per-variant deletes during a swap-in-flight cannot remove
the active variant while the pending variant is loading.
- core/inference/llama_cpp.py publishes ``loading_model_identifier``
before ``_download_gguf`` starts and clears it in ``finally``. Cache
delete (routes/models.py) and the cross-workload release helpers
(routes/inference.py::_release_llama_for and
diffusion.py::_release_chat_backend_for_diffusion) consult it so a
multi-GB HF download cannot be rmtree'd or be ignored by /images/load
while still in flight.
P2 fixes:
- core/inference/diffusion.py adds
``generate_image_with_metadata`` + ``async_generate_with_metadata``;
/images/generate uses it so the response model/family reflect the
pipeline that actually produced the image even if an unload races
the route.
- core/inference/diffusion.py: ``base_repo`` only applies when picking
a GGUF quant. Filling Base diffusers repo while loading a full
diffusers repo no longer silently swaps the load target.
- core/inference/diffusion.py: failed device placement / offload now
drops pipe + transformer references explicitly before drain so
partial allocations cannot keep VRAM around.
- core/inference/diffusion.py: torch/diffusers imports surface as a
clear RuntimeError naming the missing dependency.
- core/inference/diffusion.py: _smart_base_repo splits on both POSIX
and Windows separators so ``C:\\Users\\me\\base\\FLUX.2-klein-4B-GGUF``
no longer picks the Base 4B variant via the parent dir.
Tests:
- 6 new regression cases (Windows leaf, traversal/backslash rejection,
relative-dir local load, metadata snapshot, lock serialisation).
- All 59 diffusion backend + route tests pass.
Round 12 reviewer findings.
Backend correctness (P1)
* core/inference/diffusion.py load_model: GGUF branch now
handles an absolute local directory passed as repo_id by
joining Path(repo_id) / gguf_filename directly instead of
handing the path to hf_hub_download (which raises
HFValidationError because the path is not 'namespace/repo').
Closes round 12 review #1 -- the load request advertised
'local path' support but actually only worked for Hub repo ids.
Delete guard precision (P1)
* routes/models.py /delete-finetuned + /delete-cached:
diffusion guard now consults gguf_filename from status()
and ALLOWS per-variant deletes that target a different quant
than the one the loaded pipeline is reading. Loading
'Q4_K_S' no longer blocks deleting 'Q8_0' from the same
repo / export directory (round 12 reviews #3 and #4).
Accelerator (P2)
* core/inference/diffusion.py _drain_cuda_cache: also calls
torch.mps.empty_cache() when the MPS backend is the
active accelerator. Apple Silicon swaps now actually return
held VRAM instead of leaving it pinned in the Metal
allocator (round 12 review #10).
Smart base repo (P2)
* core/inference/diffusion.py _smart_base_repo: only inspects
the LAST segment of the repo id / path for the 'base' / '9b'
tokens. A namespace like baseorg/FLUX.2-klein-4B-GGUF or
a parent directory like /home/me/.cache/base/... no
longer falsely selects the Base variant (round 12 review #9).
Round 11 reviewer findings.
Backend lifecycle (P1)
* core/inference/diffusion.py _release_other_gpu_owners_for_
diffusion: now re-checks is_export_active() locally before
calling _shutdown_subprocess. The route layer already 409s on
active exports, but defence-in-depth means direct backend
callers (tests, scripts, future routes that forget the
higher-level guard) can no longer terminate an in-flight
export and corrupt the user's partial output.
* routes/inference.py standard chat-load path: the duplicate
inline 'if exp_backend.current_checkpoint -> _shutdown_subprocess'
block was removed. _release_export_for above already handles
settled checkpoints and skips active ones; the inline block
was the round 11 #2 asymmetric fix surface.
Routing / error mapping (P2)
* routes/training.py start_training: except HTTPException:
raise was inserted before the broad except Exception:
handler so the 409 raised by _raise_if_training_active /
_raise_if_export_active reaches the client intact instead of
being swallowed into a 500.
State publishing (P2)
* core/inference/diffusion.py load_model: success path now
clears _loading + _pending_* under _lock BEFORE returning
self.status(), so the response payload reports the resident
pipeline cleanly (no stale is_loading=true / pending_*). The
finally block remains idempotent for error / early-raise paths.
* core/inference/diffusion.py status(): nulls family /
pipeline_class while a swap is in flight (pending_repo set
and != active_repo). Previously the response paired pending
model B's repo_id with model A's family, producing a
combination that never existed.
Validation
* models/inference.py: DiffusionLoadRequest.repo_id and
base_repo length caps bumped from 256 to 1024; gguf_filename
bumped from 256 to 512. The earlier caps rejected realistic
Studio export paths (deeply nested outputs / exports
directories, especially on Windows).
Dependencies
* pyproject.toml huggingfacenotorch + studio/backend/
requirements/no-torch-runtime.txt: floor gguf at >=0.10.0
to match the diffusers requirement. Unconstrained pin allowed
a resolver to install older gguf releases that raise at
single-file load time.
Round 9 reviewer flagged a pile of handoff asymmetries: every
GPU-owning lifecycle change (training, export, chat, images) needed
its own bespoke unload sequence and they had drifted out of sync.
Some skipped llama-server is_active; some missed safetensors
loading_models; export and training did not check is_export_active.
Backend handoff (P1)
* routes/inference.py: new _release_chat_for / _release_export_for
helpers. Both treat llama-server as held when is_loaded OR
is_active, safetensors as held when active_model_name OR
loading_models is non-empty, and export as held when
current_checkpoint OR is_export_active. Both helpers run their
unloads in worker threads so async routes do not block the
event loop.
* routes/training.py: replaces its bespoke inline llama / safe /
export unload sequence with await _release_chat_for / _release_
export_for.
* routes/export.py: same swap for the chat unload chain (export
still does NOT call _release_export_for on itself).
* routes/inference.py GGUF + standard chat-load paths: now use
_release_export_for to drop a settled export, and the standard
path's llama unload now also handles is_active=True (round 9
review #8).
Backend reject-on-active export (P1 #5)
* routes/inference.py: new _raise_if_export_active. Symmetric
with _raise_if_training_active: a long-running export is
refused with HTTP 409 instead of being silently killed when
/images/load or /load arrives. Diffusion / images load and
both chat-load paths call it.
* core/inference/diffusion.py _release_other_gpu_owners_for_
diffusion: no longer tears down an in-flight export job. Only
drops a SETTLED export checkpoint (current_checkpoint
populated, is_export_active False). Round 9 review #5 -- the
previous behavior could terminate an in-flight export and
leave a partial output artifact.
Token leak via logger.exception (P1 #6)
* core/inference/diffusion.py: load-failure logging now uses
logger.error(..., exc_msg) with the already-scrubbed string
and exc_info=False. logger.exception() with the raw Exception
would expose any hf_... token that diffusers / huggingface_hub
embedded in the message or traceback locals, defeating the
earlier in-flight scrub.
Dependency pinning (P1 #11)
* pyproject.toml: huggingfacenotorch optional extra now pins
diffusers>=0.37.0. Previously the floor was only set in
studio/backend/requirements/no-torch-runtime.txt, so a normal
pip install would resolve diffusers 0.36.0 (no
Flux2KleinPipeline) and the default curated FLUX.2 klein
Images model would fail at runtime.
Cache-delete exact match (P1 #14)
* routes/models.py /delete-cached: llama.cpp and safetensors
guards now match on exact repo-id (case-insensitive) instead
of prefix. Diffusion guard already does this; the chat guards
were the remaining surface where loading org/model-v2
blocked deleting org/model.
Round 8 reviewer surfaced event-loop stalls (blocking unload from
async routes), incomplete VRAM handoff coverage (is_active /
loading_models / is_export_active not checked), token leaks via
exception messages, /v1 exposure, and several fail-open paths.
Async / event-loop
* routes/inference.py /images/unload, GGUF chat-load handoff,
safetensors chat-load handoff: blocking DiffusionBackend.unload
pushed onto asyncio.to_thread. unload takes _load_lock +
_generate_lock and can block for the full duration of an
in-flight load / generation, which was freezing the FastAPI
worker, SSE stream, and hardware poller for minutes.
* routes/export.py + routes/training.py: same to_thread wrap on
diffusion unload during checkpoint / training start.
GPU-owner handoff completeness
* core/inference/diffusion.py _release_chat_backend_for_diffusion:
llama-server now also unloaded when is_active=True (mid-download
/ startup), not only when is_loaded; flushed in-flight
safetensors loads from loading_models too.
* core/inference/diffusion.py _release_other_gpu_owners_for_
diffusion: export shutdown now also fires when
is_export_active() returns True (checkpoint not yet assigned).
Security / scrubbing
* core/inference/diffusion.py: load failure paths now scrub
hf_token from both _last_error AND the raised RuntimeError
message (the previous scrub only cleared frame locals).
Falls back to a regex strip of hf_[A-Za-z0-9]{20,} to
catch tokens that came in via huggingface_hub default caching.
* routes/inference.py: image lifecycle endpoints moved from
router to studio_router so they no longer answer under
the /v1 OpenAI-compat prefix. Studio-only side effects
(download multi-GB GGUFs, unload chat, etc.) should not be
reachable via an OpenAI-compat client.
* models/inference.py: control-char validator now also rejects
tab. Some log sinks split fields on tab; allowing it left a
log-injection surface.
Fail-closed delete guards
* routes/models.py /delete-cached: llama.cpp and safetensors
branches now fail closed with 503 when their status check
raises (matches the diffusion-side guard added earlier).
* routes/export.py: split the try/except around the training
backend so import failure falls back to 'skip' (no
core.training in this build) while a runtime failure of
get_training_backend()/is_training_active() fails closed.
* routes/models.py /delete-finetuned: diffusion guard now also
compares against relative path candidates (Path.resolve() works
on relative input). Previously a load with a relative repo_id
bypassed the guard.
CUDA cleanup ordering
* core/inference/diffusion.py: split _release() (drops local +
gc.collect) from _drain_cuda_cache() (torch.cuda.empty_cache).
Callers now drain AFTER nulling every reference so the
allocator actually reclaims the freed slabs (previously
empty_cache ran while caller still held a local, which left
the cache pinned).
Generate response (P2 #16)
* routes/inference.py: response uses status()['active_repo_id']
instead of the UI-facing repo_id, so a queued /images/load
promoting a pending model cannot mislabel the just-rendered
image with the new model's identity.
Test wiring
* tests/test_diffusion_routes.py: mount inf.studio_router on the
test app so /images/* routes are reachable now that they live
on the Studio-only router.
Round 7 reviewer surfaced a handful of swap-window races, fail-open
guards, and seed precision mismatches. This commit closes them.
Lifecycle / state (P1)
* core/inference/diffusion.py: status() now emits active_repo_id,
active_base_repo, pending_repo_id, pending_base_repo, and
pending_gguf_filename alongside the existing UI-facing fields.
During a swap (model A loaded, model B loading) the previous
coalesced 'repo_id or pending_repo_id' hid the loading target
from delete guards. Splitting the fields lets guards block
deletion of either repo currently owned by the backend.
* core/inference/diffusion.py: generate_image() now takes
_generate_lock BEFORE snapshotting _pipe / _device. Snapshotting
outside the lock let a concurrent unload/load clear or replace
the backend between the snapshot and the forward, so the freed
or swapped pipeline would still run.
Symmetric handoffs (P1)
* routes/export.py: training-active check now runs BEFORE the
chat / inference / diffusion unload helpers, so a 409 does not
leave the user's chat session torn down for nothing. Also
explicitly fails CLOSED with 503 when is_training_active()
raises.
* routes/inference.py: _raise_if_training_active now fails closed
with 503 when the training backend is importable but its status
check raises. The previous best-effort log-and-continue could
let chat / diffusion loads collide with unverifiable training.
Delete guards (P1)
* routes/models.py /delete-cached: chat guard now also blocks
when llama-server is_active (i.e. mid-download) and when the
inference backend's loading_models set contains the target.
Round 7 review #7 flagged that the PR's diffusion-side loading
guard had no chat-side parallel, so deleting a chat repo while
it was downloading could still race the cache.
* routes/models.py /delete-cached: diffusion guard iterates the
new active_* + pending_* status fields so a delete during a
swap is refused on either repo.
* routes/models.py /delete-finetuned: same active_+ pending
handling, plus the guard now also refuses deletes of a parent
directory that contains the loaded pipeline (round 7 review #6:
rm -rf /exports/flux-model/ could unlink model_index.json that
the live pipeline is reading via mmap).
Seed precision (P2)
* models/inference.py + routes/inference.py: DiffusionGenerate-
Response now carries seed_str alongside the existing numeric
seed. Seeds above Number.MAX_SAFE_INTEGER are rounded by
JSON.parse in the browser; seed_str ships full decimal
precision for display and reproduction.
* frontend/api.ts: DiffusionGenerateResponse types seed_str;
images-page.tsx prefers seed_str over seed in the figure
caption so the displayed value reproduces the image.
* frontend/api.ts: stringifyWithBigInt no longer regex-replaces
sentinel strings over the full JSON output. It pulls the seed
BigInt out, JSON-serialises the remaining payload, and splices
the seed's decimal digits into the resulting object literal at
the known position. Avoids the round 7 #10 case where a
user-supplied prompt equal to '__bigint__:123' was rewritten
into a JSON integer and rejected as a non-string prompt.
Custom HF repo (P2)
* frontend/images-page.tsx: custom panel now exposes a 'Base
diffusers repo' input that maps to DiffusionLoadRequest.
base_repo. Required when a private / mirrored GGUF needs a
non-default base (e.g. a 9B Klein transformer would otherwise
fall back to the 4B base default).
Round 6 reviewers identified several races between load / unload /
generate and several fail-open delete guards. This commit closes
them by widening the lock scope, publishing the pending load
target through status(), and switching delete guards to
fail-closed.
Lifecycle (P1)
* core/inference/diffusion.py: load_model now also takes
_generate_lock. Previous behavior released and reallocated the
pipeline while a generation forward was still iterating
denoising steps, corrupting scheduler state and stacking VRAM.
The forward only briefly touches _lock, so taking it on the
load path does not introduce a deadlock.
* core/inference/diffusion.py: unload_model now also takes
_generate_lock. Without it, /images/unload returned
is_loaded=False while a slow forward was still running, which
let chat / training / export handoffs allocate VRAM on top of
the still-resident pipeline.
* core/inference/diffusion.py: previous pipeline release now
happens BEFORE from_single_file / from_pretrained. Switching
FLUX.2 klein 4B -> 9B on a 16-24 GB GPU was failing because
the new transformer allocation overlapped the old pipe's
residency.
* core/inference/diffusion.py: failed pipeline from_pretrained
now explicitly releases the just-loaded transformer; previously
its weights stayed pinned to GPU until GC and made the next
load more likely to OOM.
Pending-target / delete guards (P1)
* core/inference/diffusion.py: load_model now publishes
_pending_repo_id / _pending_base_repo / _pending_gguf_filename
under _lock at the start of the call (and refreshes
_pending_base_repo when the smart-base / repo defaults resolve).
status() exposes those as 'repo_id' / 'base_repo' /
'gguf_filename' during is_loading=True so delete guards can see
the target before _repo_id is set on success.
* routes/models.py /delete-cached + /delete-finetuned: diffusion
status check now fails CLOSED (HTTP 503) when status() raises.
Both guards previously logged and continued, which could let a
delete proceed against a repo whose status was unverifiable.
* routes/models.py: is_loading is also blocked on both guards
so a mid-download / mid-from_pretrained rmtree is refused.
Symmetric handoffs (P1)
* routes/export.py: /load-checkpoint now refuses with HTTP 409
when training is active instead of calling stop_training().
Chat and /images/load did the same after round 5; export was
the remaining asymmetry that would silently kill a long
training run.
* routes/training.py, routes/inference.py (GGUF and standard
chat), routes/export.py: diffusion handoff now treats
is_loading as is_loaded. The diffusion backend's unload waits
on _load_lock + _generate_lock so an in-flight load completes
first.
Requirements (P1)
* requirements/studio.txt: pin python-multipart explicitly. The
Studio routes package's eager router imports include
routes/datasets.py whose FastAPI UploadFile/File validation
crashes with RuntimeError without it in fresh test envs.
Frontend (P2)
* features/images/api.ts + images-page.tsx: seed handling now
accepts the full [-2^63, 2^64 - 1] range via BigInt. The
previous safe-integer cap rejected valid uint64 seeds the
backend accepts. A small stringify helper emits BigInts as JSON
integers without touching the rest of the payload.
Tests
* test_diffusion_routes.py: load routes/inference.py via
importlib.spec_from_file_location to avoid triggering
routes/__init__.py (which would pull in training / datasets /
data_recipe imports unrelated to diffusion tests).
* test_diffusion_backend.py: status() during is_loading shows
pending repo + base; unload waits for in-flight generation.
Round 5 reviewer findings, mostly symmetric-lifecycle and input
validation gaps the earlier rounds left open.
Backend lifecycle (P1)
* routes/training.py: training start now also unloads the GGUF
llama-server subprocess; was previously only unloading the
safetensors backend, so starting training while a GGUF chat
model was loaded kept the subprocess pinned to VRAM.
* routes/inference.py: new _raise_if_training_active helper. Both
GGUF and standard chat loads, plus /api/inference/images/load,
now refuse with HTTP 409 when training is active instead of
silently stopping training to free VRAM.
* core/inference/diffusion.py: _release_other_gpu_owners_for_
diffusion no longer stops active training. The route layer
refuses the request first, so reaching the helper with training
live would only happen from programmatic backend calls; better
to surface OOM than terminate a long training run.
* core/inference/diffusion.py: BF16 dtype is now gated on
torch.cuda.is_bf16_supported. Pascal/Turing GPUs report
is_available()=True but lack BF16 ALUs; FLUX kernels then fail
inside from_pretrained. Falls back to FP16 instead of refusing.
* core/inference/diffusion.py: GGUF transformer allocation and
pipeline allocation now run AFTER releasing chat/export GPU
owners; previously from_single_file ran first and could OOM
before the intended VRAM handoff happened.
* routes/models.py: /delete-cached now also blocks delete when
diffusion is_loading=True (not just is_loaded); concurrent
delete during hf_hub_download / from_single_file would have
raced the rmtree.
* routes/models.py: /delete-finetuned now also checks the
diffusion backend before unlinking a Studio outputs/exports
path. A user who exported a FLUX LoRA locally and loaded it via
/images/load could previously rmtree the directory the
diffusion backend was reading from.
Backend correctness / safety (P2)
* core/inference/diffusion.py: _FAMILY_EXCLUDE for qwen-image now
also covers qwen_image_edit / qwenimageedit underscore spellings
so '...qwen_image_edit-GGUF' no longer misdetects as Qwen-Image.
* core/inference/diffusion.py: detect_family now scans
_FULL_REPO_FAMILIES in addition to _FAMILIES, so SDXL repos
(stabilityai/stable-diffusion-xl-base-1.0) are auto-detected
instead of failing with 'Could not infer a diffusion family'.
* core/inference/diffusion.py: generate_image now uses a separate
_generate_lock for the pipeline forward instead of holding
_lock for the whole call. status() polls and concurrent unload
requests no longer block for the full minutes-long generation.
* routes/models.py: diffusion delete guard now uses exact repo-id
match instead of prefix match; previously loading 'org/model-v2'
would block deleting unrelated cached 'org/model'.
* models/inference.py: DiffusionLoadRequest now rejects ASCII
control characters in repo_id / gguf_filename / base_repo /
family via field_validator (closes log-injection surface from
authenticated callers). Also caps lengths at 256 chars.
* models/inference.py: DiffusionGenerateRequest seed is now
bounded to the int64/uint64 range; previously a huge seed
(e.g. 2**100) passed Pydantic then crashed inside
torch.Generator.manual_seed with 'Overflow when unpacking long
long'.
Frontend (P2)
* features/images/images-page.tsx: Custom HF repo panel now
exposes a Pipeline family override dropdown; previously the
backend supported it via DiffusionLoadRequest.family but the UI
had no way to send it, so custom repos whose names did not
contain a hard-coded substring failed to load.
* features/images/images-page.tsx: handleLoad now re-fetches
status on error. The backend clears its old pipeline before
allocating the replacement; a failed swap previously left the
UI showing 'Loaded:' with Generate enabled until manual
refresh.
Tests (10 new)
* underscore qwen-image-edit exclusion + SDXL full-repo detection
* BF16 fallback when is_bf16_supported() returns False
* status() does not block while generate_image holds _generate_lock
* route layer rejects control chars in repo_id
* route layer rejects 2**100 seeds (uint64-max boundary accepted)
* route layer happy-path with negative-prompt true_cfg_scale
forwarding (Qwen/Flux) and skip-when-no-neg (distilled CFG)
QwenImagePipeline and FluxPipeline treat guidance_scale as the
distilled CFG factor and expose true_cfg_scale as the real
classifier-free guidance knob. Negative prompts only steer the
output when true_cfg_scale > 1, so forwarding only guidance_scale
left Qwen-Image on the default true_cfg_scale=4.0 and the user's
slider value silently ineffective for negative prompts.
When the loaded pipeline accepts both negative_prompt and
true_cfg_scale and the caller supplies a non-empty negative
prompt, forward guidance_scale through both kwargs so the
negative prompt actually steers generation. When no negative
prompt is supplied, true_cfg_scale is left at the model default
to avoid switching distilled CFG models into real-CFG mode (which
would double inference cost and degrade quality).
Adds two regression tests covering the forward-when-negative and
skip-when-no-negative paths.
- DiffusionBackend.status() now takes _lock so frontend polling
cannot observe a torn snapshot mid-swap.
- Scrub hf_token / pipe_kwargs / single_file_kwargs from frame
locals before logger.exception() so rich tracebacks and structlog
formatters that render locals do not leak hf_... tokens into logs.
- routes/models.py delete_cached_repo: refuse to delete the cache
underlying a currently-loaded diffusion pipeline (both the GGUF
repo and the matching diffusers base_repo). Symmetric with the
existing chat-load + GGUF guard.
- Frontend seed validation: reject non-integer and out-of-safe-
integer-range inputs instead of silently rounding via Number(),
which would otherwise send a different seed than what the user
typed.
When a swap load fails after the previous pipeline is released,
status() previously reported is_loaded=false on top of the OLD
repo/family/base_repo metadata, which the frontend then rendered
as a misleading 'still loaded: X' label. Clear all metadata
atomically with the pipe drop so a failed swap reports a clean
empty status plus last_error. Add regression test.
- detect_family adds _FAMILY_EXCLUDE so 'stable-diffusion-3.5' no
longer matches the SD3 Medium family and 'qwen-image-edit' no
longer matches Qwen-Image. Both were misleading silent loads.
- from_single_file now forwards config=<effective_base>,
subfolder='transformer', and the HF token. Diffusers-format GGUFs
(FLUX.2 klein, Qwen-Image, SD3) need the matching base config or
the transformer load picks the wrong shapes; gated GGUFs need the
token both for download and config read.
- Move _release_chat_backend_for_diffusion + new
_release_other_gpu_owners_for_diffusion to AFTER the GGUF download
and pipeline class lookup so a typo or transient Hub error does
not kill the user's currently-loaded chat model. Peak VRAM still
stays at one model's worth because the releases run right before
from_pretrained.
- _release_other_gpu_owners_for_diffusion: shut down the export
subprocess and any active training subprocess before a diffusion
load. Symmetric with the export load path.
- routes/training.py: unload diffusion before starting training so
the new subprocess does not race FLUX/Qwen for VRAM.
- routes/export.py: also unload the GGUF llama-server before export
load (the existing inference-backend unload only covered the
safetensors path).
_release_chat_backend_for_diffusion was importing
get_inference_backend from core.inference.inference (the in-subprocess
class) and calling unload_model() without the required model_name
argument. The TypeError was swallowed and the active chat model
stayed resident, defeating the chat-to-diffusion lifecycle handoff.
Switch to the orchestrator's accessor at core.inference and pass
active_model_name through, mirroring the GGUF chat-load path. Add a
regression test that stubs both backends and verifies unload_model
is called with the active model name.
- routes/export.py load_checkpoint now unloads the diffusion
pipeline alongside the existing inference + training unloads, so
an export load after Images does not OOM the export subprocess.
- Remove the 'sd3.5' alias from the stable-diffusion-3 family.
SD3.5 needs its own family + base_repo (and its own smoke test);
pairing it with the SD3 Medium base produced a misleading load.
- _smart_base_repo: pick 9B base for unsloth/FLUX.2-klein-9B-GGUF
and -base- variants per the repo id, instead of always falling
back to the 4B family default.
- pipe_kwargs use_safetensors=True so diffusers refuses pickle .bin
weights at load time (defends against compromised base_repo).
- Release the previous pipeline BEFORE allocating the new one so
peak VRAM stays at one model's worth instead of two on swap.
- Reject empty gguf_filename when repo_id ends with -GGUF; the prior
behavior tried from_pretrained on a GGUF-only repo and 500'd deep
in diffusers with a confusing model-index error.
- Status returns gguf_filename (basename) instead of gguf_path so
the local cache path / username does not leak to authenticated
Studio sessions.
- requirements/no-torch-runtime.txt: pin diffusers>=0.37.0 so older
installs cannot resolve a version without Flux2KleinPipeline.
- Frontend curated distilled klein entries now point at the
matching non-base diffusers repos (FLUX.2-klein-4B / -9B) per
the published model cards. Update api.ts to mirror the renamed
status field.
_release_chat_backend_for_diffusion now unloads both the GGUF
chat backend (llama-server) and the safetensors / HF chat backend
(get_inference_backend) before a diffusion load. Mirror the
behaviour on the chat-load side: both the Unsloth/transformers
load path and the GGUF load path now unload the diffusion pipeline
before claiming GPU memory. Closes the OOM-on-swap path flagged
by reviewers in both directions.
- unload_model now takes _load_lock so it cannot race with an in-flight
load_model and have the load thread overwrite cleared state after
unload returned is_loaded=false.
- Move stable-diffusion-xl out of _FAMILIES into _FULL_REPO_FAMILIES.
SDXL uses a UNet (no transformer GGUF path is wired); listing it in
the GGUF families panel was misleading. SDXL full-repo loads still
work via family_override='stable-diffusion-xl'.
- Result gallery now uses h-auto + object-contain so portrait /
landscape outputs render at their true aspect ratio instead of
being cropped into a square thumbnail.
Backend
- Fix FLUX.2 klein family default base_repo: black-forest-labs/FLUX.2-klein
does not exist on the Hub. Point at the Apache 2.0 4B Base instead so
the from_pretrained call works out of the box for ungated users.
- Serialise concurrent load_model calls with a dedicated _load_lock so
two /images/load requests cannot both reach pipeline_cls.from_pretrained
at the same time (would double-spend VRAM and corrupt _pipe).
- When the caller passes a full diffusers repo (no gguf_filename),
use repo_id directly instead of silently substituting the family
default. Closes the load-the-wrong-model regression flagged by review.
- Drop negative_prompt from the pipeline call when the loaded pipeline
does not accept it (FLUX.2 / FLUX.2 klein). Inspect __call__ via
inspect.signature so we do not maintain a manual class list.
- Best-effort unload the chat backend (llama-server) before a diffusion
load so a 24 GB consumer GPU can swap between chat and diffusion
without manual unload steps.
Frontend
- Replace the four curated entries with the actual filenames published
on the Hub (lowercase flux-2-klein-Nb-Q4_K_S.gguf and flux2-dev*).
- Add an explicit base_repo per curated entry so the backend never
falls back to the family default for the curated picker.
- Add the Apache 2.0 FLUX.2 klein base 4B entry so first-time users
have an ungated, no-token-required default.
- Hide the negative prompt field for FLUX.2 / FLUX.2 klein and show a
small explanatory note instead.
Tests
- Add 6 new backend tests: base_repo override, full-repo (no GGUF)
no-substitution, concurrent serialise race, signature-based kwarg
filter, negative_prompt strip on FLUX.2, negative_prompt preserved
on supporting pipelines. 33 tests passing.
Backend
- core/inference/diffusion.py: DiffusionBackend singleton that loads
diffusion GGUFs from Hugging Face via diffusers.GGUFQuantizationConfig
and runs them on the active CUDA / MPS / CPU device. Supports FLUX.2,
FLUX.2 klein, FLUX.1, Qwen-Image, Stable Diffusion 3, and SDXL.
- routes/inference.py: POST /api/inference/images/load,
POST /api/inference/images/generate, POST /api/inference/images/unload,
GET /api/inference/images/status mirroring the llama-server lifecycle.
- models/inference.py: DiffusionLoadRequest, DiffusionGenerateRequest,
DiffusionGenerateResponse pydantic schemas with prompt / step / size
validation up front so callers get clear 422s rather than VAE crashes.
- requirements/no-torch-runtime.txt: pin gguf alongside the existing
diffusers entry so GGUFQuantizationConfig works out of the box.
- tests/test_diffusion_backend.py + tests/test_diffusion_routes.py:
27 unit tests covering family detection, validation, lifecycle, and
the full FastAPI round trip with the backend stubbed. No torch /
diffusers / GPU required to run.
Frontend
- features/images/: standalone images-page.tsx with curated model picker
(FLUX.2 klein 4B / 9B, FLUX.2 dev, FLUX.1 dev), HF token field,
prompt + negative prompt, resolution presets, steps + guidance
sliders, seed input, and a result gallery that renders base64 PNGs
inline.
- app/routes/images.tsx: lazy /images route wired into router.tsx.
- components/app-sidebar.tsx: PaintBrush02Icon nav item between
Recipes and Export, hidden in chat-only mode.
* Studio: PDF / document attachments for Anthropic + OpenAI
Studio's local-GGUF chat already supports image attachments via the
`image_url` content part shape. PDFs and other documents had no
plumbing for the external-provider path: there was no normalised
content type the frontend could send that translated to Anthropic's
native `document` block or OpenAI's `input_file`.
Add a Studio-side `input_document` content part on assistant /
user messages with three shapes:
{type: "input_document",
file_data: "data:application/pdf;base64,<DATA>",
filename?: "name.pdf",
media_type?: "application/pdf"}
{type: "input_document",
file_url: "https://example.com/doc.pdf",
filename?: "doc.pdf"}
Translation:
- Anthropic Messages API: emits a `document` block with
`{source: {type:"base64", media_type, data}}` or
`{source: {type:"url", url}}`, plus an optional `title` from
`filename`. PDFs are extracted server-side by Anthropic per their
vision/document docs and counted toward input tokens.
- OpenAI Responses API: emits `{type:"input_file", file_data |
file_url, filename?}`. PDFs are extracted server-side.
Empty / unparseable `input_document` parts are silently dropped so
a malformed frontend payload can't blow up the request.
Tests:
- New `test_multimodal_document.py` with 6 cases pinning the
outbound body shape for base64 + URL inputs on both providers,
and the empty-part drop behavior on both.
- The Anthropic assertions strip the prompt-cache wrapper
(`cache_control:{type:ephemeral}` that the tail-message caching
layer adds) before comparing the document core fields, so this
test stays focused on the translation, not the caching layer.
Live verified end-to-end against both providers: a 363-byte
single-page "HELLO" PDF, base64-encoded, attached as a `document`
block to Opus 4.7 and as an `input_file` to gpt-5.5. Both models
correctly extracted the word "HELLO" from the PDF.
Follow-up (out of scope):
- Pydantic schema entry on ChatMessage.content for `input_document`
(today it rides through because ChatCompletionRequest uses
extra=allow). Will tighten when the frontend attach button lands.
- Frontend file-picker UX for non-image attachments on the external
provider path.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: gate empty-content msg + skip empty data-URI payload
Gemini High + Codex P2 on PR #5689:
1. Anthropic translation appended an empty `anthropic_parts` array
when every part was dropped (e.g. user sent only an unparseable
input_document). Anthropic 400s on "messages.N.content: at least
one block is required". Skip the whole-message append when no
parts survived. The OpenAI Responses path already had the
equivalent guard, so this brings the two providers into parity.
2. `data:application/pdf;base64,` with no payload (or whitespace-only)
parses to an empty `source.data` string. Anthropic rejects that
with 400 as well. Skip the document block before constructing it.
Plus 2 new test cases pinning both behaviors:
- `test_anthropic_empty_only_document_drops_whole_message`: confirms
a turn whose only content is an unparseable input_document does
NOT make it onto the outbound `messages` array.
- `test_anthropic_empty_data_uri_payload_is_dropped`: confirms an
empty-payload data-URI is filtered out at translation time.
(Note re: gemini's other High note about adding `input_document` to
the Pydantic ContentPart union -- ChatCompletionRequest is configured
with `extra=allow` so the part rides through today. Tightening the
union belongs with the frontend attach-button PR that surfaces the
field; called out as follow-up in the PR description.)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: register input_document in ContentPart + builder
Reviewer caught that the translation code on the external_provider
side was unreachable from a real ChatCompletionRequest:
- ContentPart is a discriminated Union of (text, image_url) only, so
any `{"type": "input_document", ...}` part was rejected by Pydantic
at request parsing with a discriminator error before the helper
could see it.
- _build_external_messages in routes/inference.py only walked text
and image_url parts, so even with a permissive schema the document
parts would have been silently dropped instead of forwarded to
the per-provider translator.
Fixes:
- Add InputDocumentContentPart with optional file_data / file_url /
filename / media_type and Tag("input_document") on the Union.
- Extend _build_external_messages to pass input_document through as
a plain dict for vision-capable providers (so external_provider's
existing Anthropic `document` and OpenAI Responses `input_file`
mappers actually run) and strip them on non-vision providers.
Tests added: schema accepts input_document, builder passes it to
vision providers, builder strips it on non-vision providers.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: validate file_data before preferring over file_url
Codex P2 caught that the OpenAI input_document translator treats any
truthy file_data as valid and never falls back to file_url. That
means a malformed `data:application/pdf;base64,` (empty payload) or
a whitespace-only data URI gets forwarded as `file_data=""` and
400s the whole turn, AND silently discards a perfectly recoverable
file_url on the same part.
Mirror the Anthropic-side guard onto the OpenAI Responses path:
treat any "data:" URI with no actual base64 payload as missing and
fall through to file_url. Standalone-empty data URIs (no fallback)
are dropped entirely instead of being sent to the wire.
Tests added: empty data URI + valid file_url -> file_url wins,
whitespace-only data URI + valid file_url -> file_url wins,
empty data URI without fallback -> part is dropped.
* Address review: Anthropic side also falls back to file_url on empty data URI
Codex P2 follow-up to my earlier fix: I added the empty-data-URI ->
file_url fallback to the OpenAI Responses translator but missed
the Anthropic translator, which still `continue`d on empty payloads
and discarded an otherwise valid file_url on the same part. Result:
when the frontend supplied both file_data (placeholder / broken)
AND a working file_url, Anthropic silently lost the attachment;
when the message contained only that part, the whole message could
be dropped before reaching the wire.
Mirrored the OpenAI guard: any "data:" URI with no actual base64
payload (`data:application/pdf;base64,` or whitespace-only) is
treated as missing, and the file_url branch takes over. The
all-parts-dropped guard further down already handles the
no-fallback case.
Tests added: empty data URI + valid file_url -> URL source on the
wire with the filename preserved; whitespace-only data URI + valid
file_url -> URL source on the wire.
* Address review: gate input_document passthrough to anthropic + openai
Codex P1: only `_stream_anthropic` and `_stream_openai_responses`
have explicit translation logic for input_document parts (the former
maps to {type:"document", source:...}, the latter to
{type:"input_file", file_data|file_url}). Every other provider
(gemini / mistral / kimi / openrouter / deepseek / qwen / custom)
goes through the generic /chat/completions passthrough that forwards
`messages` verbatim, so any input_document part on a non-vision
route on those providers would 400 with an unknown content_part
type.
Added `_INPUT_DOCUMENT_PROVIDERS = frozenset({"anthropic", "openai"})`
constant and gated the pass-through branch on `provider_type in
_INPUT_DOCUMENT_PROVIDERS`. Every other provider strips the part
(text content survives). Threaded provider_type through from
_proxy_to_external_provider's call site.
Tests updated: vision + provider in {anthropic, openai} still
forwards; six unmapped providers (gemini/mistral/kimi/openrouter/
deepseek/qwen) strip the part; missing provider_type strips
defensively. The existing non-vision drop test still passes.
* Fix stale web_fetch tool-version assertion after merging main
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: wire OpenAI Responses server-side context compaction
The OpenAI Responses API accepts a `context_management` field that
enables server-side compaction. When the rendered prompt crosses the
configured threshold, the API runs a server-side compaction step and
the request continues against the compacted prefix. No beta header
and no dated version pin are required, per the docs.
Changes:
- Add `compaction_threshold: Optional[int]` (ge=1_000, le=2_000_000)
to ChatCompletionRequest. Thread through `routes/inference.py` ->
`stream_chat_completion` -> `_stream_openai_responses`.
- In `_stream_openai_responses`, when threshold is set AND the base
URL points at cloud OpenAI (api.openai.com), attach
`context_management: [{type:"compaction", compact_threshold:N}]`
to the outbound body. Non-cloud bases (ollama, llama.cpp, "custom"
presets) silently drop the field so we don't 400 those servers.
- Add `test_openai_compaction.py` with 4 cases: cloud OpenAI sets
the field verbatim, low-threshold probe passes through (we don't
clamp on the OpenAI side because the API accepts whatever),
non-cloud base drops the field, omitted threshold leaves body
untouched.
Live verified against the real OpenAI API on gpt-5.5:
`context_management:[{type:"compaction", compact_threshold:200000}]`
returns 200 with no error.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: accept Azure OpenAI base URLs + raise compaction floor
Two reviewer follow-ups on the OpenAI compaction PR:
1. The `is_openai_cloud = "api.openai.com" in self.base_url` check
excluded Azure OpenAI Foundry, even though Azure exposes the
same /v1/responses extensions (context_management,
prompt_cache_retention, container shell). Users on Azure saw
their compaction toggle silently no-op. Broadened the check to
also match `*.openai.azure.com` and made it case-insensitive so
URLs copy-pasted from the Azure portal still resolve. Non-cloud
OpenAI-compatible servers (ollama / llama.cpp / vLLM / "custom"
preset) still fall outside the gate.
2. The schema floor on compaction_threshold was ge=1_000, which is
well below the upstream Responses API's effective minimum
(vercel/ai#12486, langchain-ai/langchain#35464 report
`compact_threshold is not enabled` 400s on Azure at 100k; cloud
uses 200k as the canonical example). Raised the floor to 10k
so obvious typos surface as a clean 422 from FastAPI rather than
an opaque upstream 400 the user has to debug from the SSE
stream.
Tests added: Azure base URL carries both context_management and
prompt_cache_retention; mixed-case Azure URLs match; schema rejects
9_999 and accepts 10_000.
* Address review: drop schema-level compaction floor (cross-provider regression)
Codex P2 follow-up on the previous floor bump: ge=10_000 was
enforced globally at the ChatCompletionRequest layer, but the field
is documented as a no-op on every non-cloud OpenAI base and every
non-OpenAI provider. With the global floor, an Anthropic / ollama
/ llama.cpp / custom request that happens to carry compaction_threshold
below 10k was rejected with 422 at request validation time instead
of being silently ignored as the description promised.
Reverted the schema floor to ge=1 (any positive int) and rewrote
the description to call out per-provider routing: OpenAI cloud's
effective floor is around 200k and surfaces upstream 400s below
that; _stream_anthropic clamps sub-50k values up. Per-provider
helpers stay the single source of truth on the floor.
Test updated to pin: zero is still rejected, but every positive
value (1, 5_000, 9_999, 10_000, 200_000) passes schema validation.
* Address CodeQL: hostname-anchored OpenAI cloud detection
CodeQL py/incomplete-url-substring-sanitization fired on
`".openai.azure.com" in _base`. An attacker who controls the
configured base_url could slip cloud-only request body fields
(prompt_cache_retention, context_management compaction, container
shell) to an arbitrary server with:
https://evil.com/api.openai.com/v1https://api.openai.com.attacker.com/v1https://attacker.com/.openai.azure.com/v1https://my-resource.openai.azure.com.attacker.com/openai/v1
Replaced the substring check with a `_is_openai_family_cloud`
helper that runs urllib.parse.urlparse on the URL and matches the
lowercased hostname exactly (`api.openai.com`) or via `endswith`
on the leading-dot suffix (`.openai.azure.com`). Both halves are
host-anchored so path / fake-subdomain bypasses fail.
Test added: every attacker-controlled bypass shape above must NOT
carry context_management OR prompt_cache_retention on the wire.
Existing Azure and openai.com tests still pass.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: scope compaction_threshold description to OpenAI on this branch
Codex P2: the field description on this PR mentioned Anthropic
compaction behavior, but the Anthropic wiring lives on PR 5686
(separate branch). On feat/openai-compaction alone, _stream_anthropic
has no compaction_threshold parameter, so the field is silently
ignored for Anthropic requests and the doc claim was misleading.
Trimmed the description to OpenAI cloud + Azure Foundry only on
this branch. PR 5686 already re-adds the Anthropic clause via its
own change, so the rebase / merge order on main will land the
combined description naturally once both PRs ship.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: wire Anthropic server-side context compaction
Anthropic ships server-side context compaction as a beta
(`compact-2026-01-12`). When the rendered prompt crosses the
configured input-token threshold, Anthropic runs an extra LLM pass
that summarises older turns and the request continues against the
compacted prefix. The response carries the original top-level fields
plus a new `context_management` block (with `applied_edits`) and
`usage.iterations[]` accounting per pass.
Per the docs the feature is currently supported on Opus 4.6, Opus 4.7,
Sonnet 4.6, and Mythos preview. The minimum threshold is 50k tokens;
under-50k requests 400.
Changes:
- Add prefix gate + helper `_anthropic_supports_compaction` plus
constants `_ANTHROPIC_COMPACTION_PREFIXES`, `_ANTHROPIC_COMPACTION_BETA`,
`_ANTHROPIC_COMPACTION_TYPE`, `_ANTHROPIC_COMPACTION_MIN`.
- Add `compaction_threshold: Optional[int]` to ChatCompletionRequest
(50k ge bound, 2M le bound). Thread through `routes/inference.py`
-> `stream_chat_completion` -> `_stream_anthropic`.
- In `_stream_anthropic`, when threshold is set AND the model
accepts compaction, attach `context_management.edits[{type:
"compact_20260112", trigger:{type:"input_tokens", value:N}}]` to
the outbound body. Sub-50k values are clamped up to 50k to keep
the request well-formed.
- Refactor the anthropic-beta header builder to merge any combination
of `code-execution-2025-08-25` + `compact-2026-01-12` flags into
one header value. Unrelated betas added at the registry level still
pass through.
- Add `test_anthropic_compaction.py` with 16 cases: gate matrix
(every doc-listed model), correct body shape, threshold clamping,
beta header merge with code execution, silent no-op on unsupported
models, omitted-threshold pass-through.
Live verified end-to-end against the real Anthropic API:
`compact_20260112` accepted on Opus 4.7, response carries
`context_management.applied_edits` + `usage.iterations[]` as
documented. (The first WebFetch-summarised version of these docs
suggested `compact_20260120`; the actual API only accepts
`compact_20260112`, matching the beta-header date. Worth pinning
behind a test so a future doc update can't drift back.)
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: drop ge=50_000 clamp + parse usage.iterations[]
Two reviewer follow-ups on the compaction PR:
1. Pydantic ge=50_000 on compaction_threshold was dead code.
FastAPI rejected sub-50k threshold values with a 422 before the
`max(int(...), _ANTHROPIC_COMPACTION_MIN)` clamp in
_stream_anthropic could ever fire. Relaxed the floor to ge=1 so
the in-helper clamp actually does its job; the schema comment
now explains why this is intentional. Added a regression test
that posts a value of 1 and 49_999 through the real request
schema.
2. Anthropic publishes per-iteration token counts in
`usage.iterations[]` whenever a fresh compaction has run, and
the top-level input_tokens / output_tokens cover only the
`message` iteration -- billing must add the compaction
iterations on top. Aggregate compaction iteration tokens into
`last_usage["compaction_input_tokens" / "compaction_output_tokens"]`
so the cost surface (PR 5690) can read them without re-walking
the array, and surface both figures in the closing stream
summary log. Added two tests: one that pins the aggregation on a
compacted turn and one that pins `None` when no fresh
iterations land (so re-applied compaction blocks don't double-bill).
Sourcing: https://platform.claude.com/docs/en/build-with-claude/compaction
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: round-trip Anthropic compaction blocks across turns
Codex P1: once context_management is enabled and Anthropic runs
server-side compaction mid-stream, the response carries a
`{type:"compaction", content:"<summary>"}` content block on the
assistant message. The translator only handled text_delta and
input_json_delta on content_block_delta, so the compaction block
was silently dropped. Worse, the request schema's ContentPart
discriminated Union didn't accept `type:"compaction"`, and
_build_external_messages didn't pass it through, so even a
hand-crafted assistant message carrying the block would 422 at
parse time. Net result: Anthropic re-compacted from scratch on
every subsequent turn, wasting input tokens and reasoning budget.
End-to-end backend wiring of the round-trip:
1. SSE translator. _stream_anthropic now tracks a `current_compaction`
state slot. content_block_start with type=="compaction" seeds it
(Anthropic may include the summary on the start event AND/OR
stream it via text_delta events on the same block index --
handle both). text_delta inside a compaction block routes into
the compaction buffer instead of the user-visible content
stream, since the summary is opaque internal state, not
assistant prose. content_block_stop emits a `compaction_block`
tool_event carrying the full summary so the chat-adapter can
persist it. compaction_blocks_seen is surfaced in the closing
summary log.
2. Pydantic schema. Added CompactionContentPart with Tag("compaction")
on the ContentPart Union so requests carrying the block parse
cleanly. Required `content` field with a docstring pointing at
the Anthropic docs.
3. Message builder. _build_external_messages forwards compaction
parts on both vision and non-vision paths; the per-provider
stream helper decides whether to forward to the wire (Anthropic
does; other providers ignore the part). When a non-vision route
ends up with a single text part, collapse back to a string
so providers that don't accept content arrays still get the
expected shape.
4. _stream_anthropic outbound translator. {type:"compaction"} parts
on an assistant message land on the wire verbatim. Empty/missing
`content` is skipped so a malformed stored block can't 400
Anthropic.
Tests added (5): stream emits compaction_block tool event with the
summary intact; user-visible content stream does NOT carry the
summary text; outbound body forwards compaction parts verbatim on
the next turn; Pydantic schema accepts the part; builder passes
it through on both vision and non-vision provider routes.
Frontend follow-up: the chat-adapter needs to persist the
compaction_block tool_event onto the stored assistant message so
turn N+1 includes it in payload.messages. Pinned in the PR
description.
Sourcing: https://platform.claude.com/docs/en/build-with-claude/compaction
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: gate compaction-part passthrough to Anthropic only
Codex P1: my previous round-trip change preserved {type:"compaction"}
parts on every provider route in _build_external_messages. That
meant a chat history with prior compaction state silently leaked
the Anthropic-specific block to OpenAI/DeepSeek/Mistral/Gemini/
Kimi/OpenRouter on a provider switch, where generic
/chat/completions passthrough hands the unknown content type to
the upstream API and 400s the whole turn.
Added a `provider_type` kwarg to _build_external_messages and
gated the compaction forwarder on `provider_type == "anthropic"`.
Every other value (including the legacy None for callers that
don't pass it yet) strips the part. The Anthropic stream helper
still maps it to a native `compaction` block on the wire.
Threaded provider_type through from _proxy_to_external_provider's
call site.
Tests updated: vision + provider="anthropic" still forwards; six
non-anthropic providers strip the part; missing provider_type
strips defensively; non-vision + anthropic still forwards; non-vision
+ non-anthropic collapses back to a text string.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: wire Anthropic web_fetch server-side tool
Studio's Anthropic passthrough only forwarded web_search and
code_execution when enabled_tools was set. Asking Claude through Studio
to fetch a URL produced no fetch (the tool was not in the outbound
tools array), so users had to fall back to web_search even when they
already had the exact URL they wanted.
This change opts in web_fetch_20250910 when enabled_tools contains
"web_fetch". The new tool entry is appended alongside any existing
web_search / code_execution entries:
{"type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 5}
No anthropic-beta header is required (web_fetch is GA); the existing
code-execution-2025-08-25 flag continues to merge cleanly when both
tools are enabled in the same turn.
SSE translation mirrors the web_search path. A `server_tool_use` block
with name="web_fetch" emits a `tool_start` _toolEvent carrying the
URL the model asked to fetch; the matching `web_fetch_tool_result`
block emits a `tool_end` _toolEvent whose result string follows the
Title / URL / Snippet shape parseSourcesFromResult on the frontend
already expects, so the source pill renders identically. Error blocks
(`web_fetch_tool_error`) are surfaced as "Error: <error_code>" matching
the code_execution error path.
The final "Anthropic stream complete" log line picks up web_fetch_
requested / web_fetch_invocations / web_fetch_urls so support reports
of "the model did not fetch anything" can be triaged from the log.
Verified end to end against claude-haiku-4-5 with
`enabled_tools=["web_fetch"]`: the model emitted tool_start with
url=https://example.com and tool_end with the page Title + URL +
Snippet, plus the assistant message correctly read back "Example
Domain" as the title.
Tests:
- 5 new unit tests in test_anthropic_web_fetch.py covering tool
registration, the combined web_search + web_fetch + code_execution
request body, the pill-off case, and SSE translation for both
success and error paths.
- All 242 existing Anthropic + OpenAI provider tests still pass.
The enabled_tools field description in models/inference.py is updated
so OpenAPI consumers see the new option.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* web_fetch: title fallback to URL, log parse failures, drop dead checks
Three review nits on the previous commit:
1. `_format_web_fetch_result` left `title` empty when Anthropic omitted
`document.title`. The frontend `parseSourcesFromResult` only emits
a source pill when both `Title:` and `URL:` lines are present, so
fetches against pages without an HTML title tag silently lost
their citation in the UI. Fall back to `title = title or url`,
matching the web_search formatter.
2. The broad `except Exception` around `json.loads(buffer)` for the
web_fetch input swallowed the failure with no trace. Log at debug
so a malformed partial_json buffer can be triaged from the server
log without changing behavior.
3. `inner` was already sanitised to a dict at the matching
content_block_start and `_format_web_fetch_result` always returns
a non-empty string (defaulting to "(fetch complete)"), so the
`isinstance(inner, dict) else {}` guard and the
`result_text or "(fetch complete)"` fallback at the emit site
were dead code. Removed.
Added a test exercising the titleless path so the fallback stays
covered.
* chat-adapter: emit source pills for web_fetch tool calls
`parseSourcesFromResult` was only wired up for tool calls where
`toolName === "web_search"`, so the Title / URL / Snippet block the
backend formatter emits for `web_fetch_tool_result` never reached the
source-pill renderer. Users saw the raw tool result in the tool card
but the dedicated source-pill row at the message tail stayed empty.
Both web_search and web_fetch ship the same text shape today, so the
fix is to broaden the gate.
* Address review: wire web_fetch from Search pill + fix pause_turn truncation
Two reviewer follow-ups on the Anthropic web_fetch PR:
1. The backend tool wiring landed but the frontend chat-adapter
never put `web_fetch` in `enabled_tools`, so toggling the Search
pill only ever attached `web_search` -- web_fetch was unreachable
from the UI. Added providerSupportsBuiltinWebFetch() (Anthropic
today) and paired the entry with the existing Search pill, since
the canonical workflow is "search returns URLs, fetch reads
them" and there is no separate UI toggle yet.
2. `pause_turn` from Anthropic's stop_reason vocabulary fell through
the finish_reason map's "stop" default, which the OpenAI-format
client renders as end-of-message and truncates the answer. Per
the docs pause_turn means "Claude paused a long server-tool
turn (web_search / web_fetch) and will resume". Mapped to None
and skipped the chunk emission so the SSE stream still ends with
[DONE] on message_stop but no terminal finish_reason lands on
the client. While there: added explicit mappings for `tool_use`
(-> tool_calls) and `refusal` (-> content_filter) which were
also falling through to "stop".
Tests added: pause_turn emits no finish_reason, end_turn still
emits "stop", refusal maps to "content_filter".
Sourcing: https://platform.claude.com/docs/en/api/messages#response-stop-reason
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: per-session cost calculator + /api/providers/pricing endpoint
Neither the Anthropic Messages API nor the OpenAI Responses API
reports a `cost` field on the response. Both expose detailed token
counts (input, output, cache hits, server-tool invocations); pricing
multipliers live in the provider docs. The frontend's "cost so far"
display was impossible without scraping the server log.
Land the math + a snapshot endpoint so the cost calculator can run
client-side from the existing usage chunk plumbing. The actual UI
hookup belongs in a frontend follow-up (and is gated on PR #5670's
usage-chunk emission landing so the frontend sees the usage block
in the first place).
Changes:
- New `core/inference/pricing.py` with:
- Per-MTok base pricing tables for every active Anthropic and
gpt-5.x family member. Dated snapshots inherit the canonical-id
price via prefix match so future snapshots cost the same as the
canonical id until pricing changes.
- Shared multipliers for Anthropic cache writes (5m: 1.25x, 1h: 2x)
and reads (0.1x); OpenAI cache reads (0.1x); Anthropic server
tool surcharges ($10 / 1k web_search, $0.05 / hour code_exec
beyond the 50-hour daily free tier).
- `calculate_cost(provider, model, usage)` returns a per-turn USD
breakdown plus billable token counts, with priced=False for
unknown models so the UI can still render token counts.
- `pricing_snapshot()` returns the whole table for the frontend
so it doesn't re-implement the multipliers.
- New `GET /api/providers/pricing` returning the snapshot, scoped
behind the existing auth dependency.
- New `backend/tests/test_pricing.py` with 12 cases pinning the
math against documented values: base input/output multiplication,
5m / 1h / read multipliers, default-to-5m fallback when the
breakdown is absent, web_search per-1k pricing, code_execution
per-hour pricing, dated-snapshot fallback, OpenAI cache-read
discount accounting (cached tokens subtracted from full-price
bucket and re-billed at 0.1x), unknown model graceful-degrade,
and the snapshot endpoint shape.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Studio: verified OpenAI pricing + fix billable input double-count
Address the cost-calculator review:
- OpenAI prices were 2-6x under the actual published rates.
Cross-checked the live developers.openai.com/api/docs/pricing page
and replaced every entry. gpt-5.5 is 5/30, gpt-5.5-pro is 30/180,
gpt-5.4 is 2.5/15, gpt-5.4-mini 0.75/4.5, gpt-5.4-nano 0.20/1.25,
gpt-5.3-codex 1.75/14. Added chat-latest alias to the canonical
chat-snapshot rate. Dropped o3 / o4 / gpt-4.5 rows that are no
longer listed on the page; calculator returns priced=False instead
of silently billing at zero.
- billable_input_tokens was double-counting cached tokens for
OpenAI. Anthropic excludes cache_* buckets from input_tokens so
we add them; OpenAI folds cache_read_input_tokens into
input_tokens already, so the tooltip read 1.8M for a 1.0M bill.
Branched the math by provider and added a regression test.
Sourcing notes in the module docstring updated.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Address review: canonical 4.5 ids, long-context tier, OpenAI tool fees
Three Codex P1 follow-ups on the cost calculator:
1. Canonical Anthropic 4.5 ids missing from ANTHROPIC_PRICING.
claude-opus-4-5 / claude-sonnet-4-5 / claude-haiku-4-5 (no date
suffix) are the ids used by backend defaults
(PROVIDER_REGISTRY['anthropic'].default_models), but the table
only had the dated forms. _lookup's prefix fallback doesn't help
because the canonical id is SHORTER than the dated key, so
str.startswith goes the wrong way and the calculator returned
priced=False + zero cost. Added the canonical aliases for
opus-4-5, sonnet-4-5, haiku-4-5, and opus-4-1.
2. OpenAI long-context tier. gpt-5.5 and gpt-5.4 cross over at
272k input tokens to a 2x input / 1.5x output rate (gpt-5.5:
$5/$30 -> $10/$45; gpt-5.4: $2.50/$15 -> $5/$22.50). Turns past
the threshold were systematically undercounted at headline
rates. Added long_context_threshold / long_context_input_per_mtok /
long_context_output_per_mtok columns and a tier-selection step
in calculate_cost; model_priced gains a "(long-context >272000)"
suffix when the higher tier applies so the tooltip can show
which rate was used. gpt-5.5-pro / gpt-5.4-pro / mini / nano /
codex have no published long-context tier today, so they keep a
single rate.
3. OpenAI server-tool surcharges. web_search is $10/1000 calls and
the hosted shell container is $0.03 per 20-minute session on the
default 1g tier (~$0.09/hr). server_tools_usd was previously
stuck at 0.0 for OpenAI even when web_search and shell tools
fired, so sessions with tool use understated cost. Added
OPENAI_WEB_SEARCH_USD_PER_1K and OPENAI_CONTAINER_USD_PER_HOUR
constants plus a parallel of the Anthropic surcharge block that
reads counts from usage["openai_tool_use"]. The SSE translator
wires the counts in a follow-up commit; the calculator is now
ready for them. pricing_snapshot also exposes both constants so
the frontend tooltip can render the per-call rate.
Existing tests updated to stay in the short-context tier where they
were testing base rates; new tests pin canonical 4.5 lookups,
long-context crossover on gpt-5.5/gpt-5.4, the absence of crossover
on mini/nano/codex, and OpenAI tool surcharges (web_search,
container hours, combined total).
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: wire OpenAI image_generation tool
OpenAI's Responses API exposes server-side image generation as a
tool entry (`{type: "image_generation"}`); the result comes back as
an `image_generation_call` output item with the base64 image on
`result`, the actual prompt used on `revised_prompt`, plus `size`,
`quality`, `output_format`, `background`. The model decides when to
call the tool based on the user's request; rendering uses one of
the gpt-image-* backbones server-side.
Available on every gpt-5.x family member plus gpt-4.1, gpt-4o, o3,
o4-mini per the docs.
Changes:
- Append `{type:"image_generation"}` to the Responses request tools
array when `enabled_tools` carries `image_generation` AND the base
URL points at cloud OpenAI. Non-cloud bases (ollama, llama.cpp,
"custom" presets that collapse to provider="openai") silently drop
the tool to avoid 400s.
- Mirror the same logic in `_build_body` (the post-expiry retry
builder) so retries carry the same tool set as the original
attempt.
- Handle `image_generation_call` items in
`response.output_item.done`: emit `tool_start` with
`arguments:{kind:"image", prompt:<revised_prompt>}` and `tool_end`
with `image_b64`, `image_mime`, `size`, `quality`, `background`
so the chat adapter can render an inline preview. Image bytes go
on the tool_end chunk; no extra fields on the chat-completions
envelope so the OpenAI SDK shape stays clean.
- Add `import time` (used for synthesised tool_call_id fallback).
- Add `test_openai_image_generation.py` with 5 cases: tool entry on
cloud OpenAI, combined with web_search + code_execution
(verifies all three coexist), non-cloud drop, omitted pill leaves
body untouched, output item translation produces the expected
tool_start + tool_end chunks.
Live verified end-to-end: `gpt-5.4-mini` with `image_generation`
tool returned an `image_generation_call` carrying ~1MB of base64
PNG plus the gpt-image backbone's revised prompt.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Use time.time_ns() for synthesised image_generation tool_call_id
Gemini medium on PR #5688: `int(time.time() * 1000)` has 1ms
resolution; two image generations resolving in the same millisecond
would collide on the synthesised id. Bump to nanoseconds.
(In practice the upstream `image_generation_call` item always carries
its own `id`; the synthesised fallback only fires when OpenAI omits
it -- rare, but cheap to harden.)
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: support Anthropic 1h cache TTL via prompt_cache_ttl field
Anthropic exposes two ephemeral cache pools per request: the default
5-minute pool, and a 1-hour pool selected by attaching `ttl:"1h"` to
the `cache_control` marker. 1h writes are billed at 2x base input vs
1.25x for 5m, but reads stay at 0.1x for both, so a single extra read
landing more than 5 minutes after the write pays off the premium.
Studio hardcoded the 5m pool via `cache_control: {type:"ephemeral"}`
on both breakpoints. For chats with multi-minute idle gaps (people
juggling tabs, long-running tool calls between turns), the cache
expires before the next turn and every read becomes a cache_creation,
not a cache_read -- exactly the case where the 1h pool wins.
Changes:
- Add `prompt_cache_ttl: Optional[Literal["5m", "1h"]]` to
ChatCompletionRequest. Default (None) preserves today's 5m behavior.
- Thread through `routes/inference.py` ->
`stream_chat_completion` -> `_stream_anthropic`.
- Build a shared `cache_marker` dict in `_stream_anthropic`; attach
`ttl` only when the request asks for one of the two valid values.
Unknown TTL strings are silently dropped to avoid sending malformed
markers (the upstream API would 400).
- Apply the same marker to both existing breakpoints (system block at
line 1175 and the latest-message tail at line 1198 / 1213) so the
pool selection is consistent across the whole prefix.
- Add `test_anthropic_cache_ttl.py` with 11 parametrized cases
pinning the outbound body shape: omitted -> default marker;
explicit `5m`/`1h` -> ttl field set; unknown values dropped;
caching off -> no markers at all.
Verified upstream that `cache_control: {type:"ephemeral", ttl:"1h"}`
is accepted by the Anthropic API today; no beta header required.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Relax prompt_cache_ttl to Optional[str] (Codex P1)
Declaring `prompt_cache_ttl` as `Optional[Literal["5m", "1h"]]` made
FastAPI/Pydantic 422 the request before _stream_anthropic could even
see the field. The whole point of the downstream drop-unknown-values
behaviour was to keep a stale frontend from crashing the request;
the strict Literal at the request layer defeated that.
Loosen the schema to Optional[str]; the existing in-helper guard
already restricts forwarded values to {"5m", "1h"} (everything else
is silently dropped). Test suite stays unchanged -- the bogus-value
cases in test_anthropic_cache_ttl.py already pass arbitrary strings
through and assert they are dropped before the wire.
* Address review: confirm extended-cache-ttl beta header is GA
Reviewer asked whether the 1h cache TTL still requires the
`extended-cache-ttl-2025-04-11` anthropic-beta header. Investigated:
- Live-tested api.anthropic.com on claude-opus-4-7 (2026-05-22)
with cache_control={type:"ephemeral", ttl:"1h"} and NO beta
header. Got status 200 and ephemeral_1h_input_tokens populated
on the create turn, plus cache_read_input_tokens populated on
the reuse turn.
- Cross-checked the current prompt-caching docs: no mention of
any beta header on the 1h TTL path.
Conclusion: the gate has been promoted to GA. The code already
does not send the beta header (the cache_marker dict only carries
`type`/`ttl`), so no wire change is needed. Pinned the contract
with two regression tests that assert the header is NOT on the
outbound request, and added a docstring note explaining the
investigation outcome so a future reader does not re-add it.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: per-model Anthropic server-side tool versions
Anthropic ships date-pinned tool versions per model family. Studio
currently hard-codes `web_search_20250305`, `web_fetch_20250910`, and
`code_execution_20250825` for every model, which means Opus 4.6/4.7,
Sonnet 4.6 and the Opus/Sonnet 4.5 family never get the newer
`_20260209` / `_20260120` variants. Those newer variants add dynamic
filtering (Claude writes code to rank/filter web results before they
enter context) and REPL state persistence + programmatic tool calling
inside the sandbox, which is what the user-facing pills are supposed
to expose.
Hardcoding the legacy versions also breaks if a future model family
drops the legacy types: the request 400s instead of falling back.
Changes:
- Add `_anthropic_web_search_version`, `_anthropic_web_fetch_version`,
`_anthropic_code_execution_version` helpers that pick the newest
variant the model accepts and fall back to the GA versions for
everything else.
- Add `_ANTHROPIC_CODE_EXECUTION_BETA` constant since the beta header
(`code-execution-2025-08-25`) is shared across both code-execution
date variants per the upstream docs.
- Wire the helpers into `_stream_anthropic` so the outbound body
carries the right pinned version per request.
- Add parametrized dispatch tests in
`test_anthropic_tool_versions.py` covering Opus 4.7/4.6/4.5,
Sonnet 4.6/4.5, Haiku 4.5, Opus 4.1/4.0, Sonnet 4.0, 3.5 Sonnet,
plus streaming integration tests that verify the outbound body
uses the right versions on Opus 4.7 (new web_search + new
code_execution), Haiku 4.5 (legacy both), and Sonnet 4.5 (legacy
web_search + new code_execution).
- Update existing `test_anthropic_code_execution.py` cases that
pinned the old version on Opus 4.7 to expect the new ones.
Verified end-to-end against the live Anthropic API: Opus 4.7 with
both pills enabled accepts the newer-pinned tools without a 400, and
Haiku 4.5 still works on the legacy fallback path.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Studio: surface prompt-cache token counts in /v1/chat/completions usage chunk
Studio's Anthropic and OpenAI Responses proxies already capture
cache_creation_input_tokens, cache_read_input_tokens (Anthropic) and
input_tokens_details.cached_tokens (OpenAI), but they were only written
to the structlog stream. Browser and SDK clients had no way to compute
"how many tokens hit the prompt cache" without scraping the server log,
so the chat UI could not show users how much money the cache was
saving on each turn.
This change emits one extra OpenAI include_usage-style chunk
(choices: [] with a populated usage block) just before the existing
[DONE] for Anthropic and after the final finish_reason chunk for
OpenAI Responses (both response.completed and response.incomplete).
The chunk shape:
usage.prompt_tokens_details.cached_tokens
normalised cache-read count, present for both providers.
usage.cache_creation_input_tokens
Anthropic-only; tokens billed at the cache-write premium.
usage.cache_read_input_tokens
Anthropic-only; same value as cached_tokens, kept for callers
that already key off the native Anthropic name.
Smoke verified end to end against a live Studio (claude-haiku-4-5
and gpt-4o-mini) plus 7 new unit tests on the helper and the two
streaming paths.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Anthropic: include cache buckets in prompt_tokens / total_tokens
Anthropic's `input_tokens` field excludes the cache buckets -- the
real prompt size is `input_tokens + cache_creation_input_tokens +
cache_read_input_tokens`. Previously the new usage chunk reported
only `input_tokens` as `prompt_tokens`, which heavily undercounted
cache-hit turns (e.g. an 18.9k-token cache_read turn looked like an
8-token prompt) and broke any downstream context / cost display fed
by `prompt_tokens` or `total_tokens`.
Fix `_build_usage_chunk` to sum all three input buckets for the
Anthropic provider while keeping the OpenAI Responses path unchanged
(OpenAI already folds cached tokens into `input_tokens`). The native
`cache_creation_input_tokens` / `cache_read_input_tokens` keys and
`prompt_tokens_details.cached_tokens` mirror are still emitted, so
clients keep full visibility of the cache split.
Tests updated to assert the summed shape.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* studio: settle GPU VRAM after killing llama-server before the next reload
The NVIDIA driver reclaims a dead process's CUDA allocations
asynchronously after the kernel reaps the PID -- typically tens to
hundreds of milliseconds. Sampling `_get_gpu_free_memory` in that
window reads artificially low, which propagates into `_select_gpus`
/ `_fit_context_to_vram` and flips the layer-split toward `--fit on`
with more CPU-offloaded layers than steady-state would have required.
On a tight VRAM card the resulting mmap thrash + OOM matches the
Apply-reload kill path that bare-shell launches with the same flags
never hit (continues the lineage of #5161 / #5401 / #5427).
Adds `LlamaCppBackend._wait_for_vram_settle`: bounded poll of
`_get_gpu_free_memory` that returns as soon as two consecutive
samples agree per-GPU within `max(256 MiB, 2% of larger sample)`,
or `max_wait` (default 2 s) wall-clock elapses with probe time
included in the bound. Records `_last_kill_monotonic` inside
`_kill_process`'s `finally` block so the wait engages on both
in-process `load_model -> _kill_process -> load` and the frontend
chat-settings Apply path (`/unload` then `/load`). The call site
runs OUTSIDE the broad `self._lock` so concurrent `/unload`,
`/cancel`, `/status` are not blocked during the wait.
Short-circuits at zero cost on cold start (no kill recorded), stale
kill (older than 15 s, driver has already settled), CPU-only host
(probe returns empty), and probe exceptions (nvidia-smi gone away).
11 new unit tests in `test_llama_cpp_wait_for_vram_settle.py` cover:
cold-start zero cost, stale-kill skip, slow-probe deadline bound,
GPU index-set change, per-GPU stability with one draining card, the
2 % adaptive tolerance, _kill_process timestamp recording on real
kill vs no-op, and an `inspect.getsource` contract that pins the
call site to outside the Phase 3 lock and uses `_last_kill_monotonic`
so a future refactor can't silently regress any of these properties.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: Michael Han <michaelhan2050@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* studio: unblock /load event loop on detect_audio_type (#5642, #5635)
studio/backend/routes/inference.py wraps llama_backend.detect_audio_type
in await asyncio.to_thread() so its chain of sequential sync
httpx.Client.post() probes (/tokenize and /detokenize, 10 s timeout
each) runs on the threadpool instead of blocking the FastAPI event
loop. Without this wrap, /api/inference/load-progress polling and any
other in-flight HTTP request stalls for up to ~80 s while
detect_audio_type runs, which is exactly the "llama-server logs say
ready, Studio UI never finishes loading" symptom in #5642 (Win10) and
#5635 (Win11). The matching init_audio_codec call on the next branch
was already wrapped; this just brings detect_audio_type to parity.
Add a CPU-only spoof-based test suite under tests/studio/load_freeze/:
- llama_server_shim.py: stdlib http.server that answers /health,
/props, /tokenize, /detokenize, /completion with per-request
delay knobs.
- test_load_orchestrator.py:
* test_buggy_route_blocks_event_loop -- behavioural canary:
with a sync detect_audio_type call, concurrent /health
requests stall for >= one tokenize delay (proves the bug
class, runs from worker threads against a real uvicorn).
* test_fixed_route_keeps_event_loop_responsive -- with the
to_thread wrap, concurrent /health latency stays under 250 ms.
* test_routes_inference_wraps_detect_audio_type_in_to_thread --
static guard so the fix cannot regress silently.
* test_fast_path_load_completes_quickly -- regression budget
for post-_wait_for_health work.
Add .github/workflows/studio-load-orchestrator-ci.yml. CPU-only,
no torch, no real llama.cpp binary, no GPU. Cross-OS proof
(ubuntu-latest / macos-14 / windows-latest, 4 passed in 7-10 s each)
ran green on danielhanchen/unsloth-staging-2#136 before landing here.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: expand load-orchestrator suite to 22 tests (failure modes, stress, drift)
Replace the 4-test smoke with a comprehensive 22-test simulation
covering every failure mode of the /load -> detect_audio_type path:
1. Behavioural canary (2) - sync vs to_thread under slow shim
2. Functional equivalence (5) - sync == to_thread for each codec
branch (None / snac / csm / whisper
/ bicodec)
3. Failure modes (5) - shim returns 500, malformed JSON,
connection reset, unreachable port,
backend not loaded
4. Concurrency / stress (2) - 50 concurrent /probe; 100-burst
/health during slow /probe
5. Drift / regression guards (3) - wrap on production source, neighbour
init_audio_codec still wrapped, no
bare detect_audio_type() in any
async route
6. Timing budgets (2) - fast-path under 2s; 5 sequential
/probes under 10s
7. Browser-compat (2) - Content-Type + JSON.parse round-trip
+ response shape stable sync vs fix
8. Cancellation (1) - client disconnect mid-probe; server
keeps serving /health afterwards
Extended llama_server_shim with knobs for HTTP-500, malformed-JSON,
connection-reset, and tok_response_map / detok_map so we can
synthesise the exact request/response shape that triggers each codec
match. No new dependencies, still CPU-only and stdlib-driven.
Cross-OS validation on danielhanchen/unsloth-staging-2#136:
- ubuntu-latest: 22 passed in 19.59s
- macos-14: 22 passed in 22.07s
- windows-latest: 22 passed in 38.79s
Cross-Python on Linux (3.10 / 3.11 / 3.12 / 3.13 x pinned-floor /
latest deps, 8 uv venvs): 176/176 passed.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: move audio detect/codec init inside load_model lock; relax small-quant CI
Follow-up to #5642 fix that addresses two distinct concerns raised by
the gemini-code-assist review on PR #5669:
1. Race condition (medium-priority comment on routes/inference.py:869)
The original fix wrapped llama_backend.detect_audio_type in
asyncio.to_thread. That unblocks the FastAPI event loop but opens
a race window where a concurrent /api/inference/load can acquire
_serial_load_lock, kill the live llama-server, and start a new
one while the first request's detect_audio_type thread is still
probing the (now-dead) port -- the route then writes stale
_is_audio / _audio_type onto the shared backend instance.
Fix: move detect_audio_type + init_audio_codec INSIDE
LlamaCppBackend.load_model, immediately before the function
returns True. Both calls happen while self._serial_load_lock is
held, so the entire load sequence (spawn, wait health, detect
audio, init codec, return) is atomic. routes/inference.py now
just reads the cached _audio_type / _is_audio attributes.
This is the shape the gemini reviewer recommended, and it also
simplifies the route -- no more asyncio.to_thread wrap, no more
conditional init_audio_codec call. The route layer keeps its
non-inference responsibilities (_native_display_label /
_native_grant_backed assignments) since those depend on
route-local arguments.
2. Hardcoded local file path in test shim (gemini's other comment)
FakeLlamaServer's default model_path was a developer-specific
Windows cache path. Replaced with an OS-portable placeholder.
The value is cosmetic-only -- only used in the synthesised stdout
template's "loading model" line, which the production code we
drive from the tests does not parse.
3. Existing CI flake on studio-inference-smoke.yml (generalised fix)
Studio GGUF CI has been red on main and 5+ unrelated PRs all
day. Root cause: small-quant Qwen3.5-2B drifts in two places.
(a) The python tool spits back "55,888" instead of "56088"
even though the tool itself returned the correct value. (b) The
OpenAI / Anthropic determinism check sees occasional non-byte-
identical responses at temperature=0.0 across runs due to KV
cache / speculative-decoding non-determinism. Both are model
output drift, not Studio regressions.
Generalised fix: match the Windows variant's already-lenient
WARN-when-tool-ran-but-model-drifted pattern. SSE-stream-empty
stays a hard FAIL (real plumbing failure); a non-empty stream
with the wrong numeric content becomes a WARN. Determinism
check similarly demotes "trailing whitespace OK but content
diverged" to a WARN; the harder grounding assertions on
later turns (paris present somewhere, turn-1 contains '1')
remain strict and continue to catch real regressions.
Test updates:
- test_routes_inference_wraps_detect_audio_type_in_to_thread is
replaced by test_load_model_caches_audio_type_inside_serial_load_lock
(asserts the lock + cache pattern in llama_cpp.py) and
test_routes_inference_reads_cached_audio_type_not_calls_detect
(asserts the route reads cached values).
- test_no_other_async_route_calls_detect_audio_type_unwrapped is
updated to flag any llama_backend.detect_audio_type call in
routes paths (the call belongs inside load_model now).
Local cross-Python matrix (Linux, Python 3.10 / 3.11 / 3.12 / 3.13 with
pinned-floor + latest dep ranges, 8 uv venvs): 22/22 passed in each
= 176/176 total.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: tool-actually-ran assertion (chatgpt P1); shim port-0 (gemini)
Two PR-review follow-ups on #5669:
1. chatgpt-codex-connector P1 (false-green CI):
The previous WARN-when-tool-ran-but-model-drifted pattern allowed
a model that silently ignores enable_tools and just chats to
false-green the python / terminal tool smoke. Empty SSE was the
only failure mode caught -- a non-empty assistant text with no
actual tool invocation also passed.
Fix: post_sse now also returns the raw event payloads. A new
helper _tool_invoked(events, expected_outputs=...) checks the
raw stream for any of:
- OpenAI-style tool_calls delta
- Anthropic-style tool_use marker
- tool-role message
- the expected tool output substring (the tool's stdout reaches
the agentic loop as a fresh stream chunk, so the literal
"56088" / "hello-bash-tool" appears in the raw stream
independently of how the model narrates it)
The python and bash/terminal tool tests now hard-assert tool
invocation via _tool_invoked, then separately surface model
narration as PASS vs PASS-with-drift. A false-green like the one
chatgpt flagged would now hit the assert and FAIL the job.
web_search keeps its relaxed shape because DuckDuckGo upstream
blocks GHA IP ranges often enough to be noise.
2. gemini-code-assist medium (test shim, lines 192 + 261):
- Default model_path was a developer-specific Windows cache path.
Already replaced last cycle with an OS-portable placeholder.
- _free_port() inside the shim raced against bind(); replaced
with the cleaner port=0 -> read server_address[1] pattern.
The unused _free_port helper inside the shim is removed.
Local sim suite still green (22 passed in 19.91s). Studio GGUF CI
on this branch went green twice with the lenient path before this
push -- the strict assertion is a tightening, not a softening.
* ci(studio-inference-smoke): broaden tool-invocation markers
Add tool_status / tool_start / tool_end / tool_result to the
_tool_invoked marker tuple in studio-inference-smoke.yml. Studio's
routes/inference.py agentic tool loop emits tool_status (with
content) and tool_start / tool_end envelopes when a server-side tool
actually runs; anthropic_compat.py emits tool_use / tool_result.
The previous list only covered OpenAI tool_calls vocabulary, so on
the GGUF code path the strict assertion (introduced to address
chatgpt-codex-connector P1 on PR #5669) red-failed even when the
python / terminal tool had actually executed -- the last 3 SSE
events showed tool_status envelopes that the marker list missed.
Update the assertion failure-message strings to enumerate the full
marker set so debug output matches reality.
Local sim suite remains 22/22 green.
* studio: address chatgpt-codex P1+P2 follow-ups on 237052ff
P1 (.github/workflows/studio-inference-smoke.yml): tighten
_tool_invoked so it only counts strong markers. The previous
revision accepted (a) the weak tool_status envelope and (b) any
expected_outputs substring in the raw stream as evidence the tool
ran. Both let the test false-green:
- tool_status fires on every iteration boundary of Studio's GGUF
tool stream (including empty {"type":"tool_status","content":""}
cursor resets) regardless of whether any tool_call was actually
produced.
- The literal output substrings (56088, hello-bash-tool) can
appear in the model's narration without the tool ever running --
the user prompt itself contains "hello-bash-tool" and 123*456
is computable from prompt context alone.
Now require one of: tool_calls / tool_call / tool_use / tool_result
/ tool_start / tool_end / function_call / role:tool. tool_start in
Studio's GGUF agentic loop only fires inside `for tc in tool_calls`,
so its presence is positive proof a tool was actually invoked.
P2 (studio/backend/core/inference/llama_cpp.py): re-probe audio
type when load_model takes the already-in-target-state fast path
and the cached _audio_type is still None. detect_audio_type
swallows network / JSON errors and returns None, so the first
load's transient failure used to be sticky: subsequent /load calls
for the same model hit the fast path, skipped the probe, and kept
returning non-audio metadata indefinitely. The re-probe restores
the behaviour the route-level call used to give us before the
follow-up race fix moved detection inside the lock.
Local 22-test load_freeze sim suite remains green.
* studio: hard-assert tool_end.result for python+bash tools
Addresses chatgpt-codex-connector P1 review on PR #5669 commit
1a2fba84 ("Keep tool-output assertions hard-failing").
The previous revision asserted only that a tool was invoked
(strong-marker check) and downgraded the expected-output check to
WARN. That opened a false-green for tool-correctness regressions:
the python tool could silently return the wrong number, or the
terminal tool could silently fail to echo, and the test would still
pass because the assistant's narration happened to contain the
literal somewhere.
Add `_tool_output_contains(events, *needles)` which parses each SSE
event payload as JSON and checks the *tool's own output* across
three native shapes:
1. Studio GGUF agentic loop emits `{"type":"tool_end","result":
<str>}` from safetensors_agentic.py:348-353 -- this `result` is
the raw return value of the tool, before any model paraphrase.
2. Anthropic compatibility layer emits `{"type":"tool_result",
"content":[...]}` from anthropic_compat.py:357 -- check the
text blocks.
3. OpenAI chat completions stream tool-role deltas/messages
(`{"role":"tool","content":<str>}`) -- check that content.
Hard-assert that:
- python tool's tool_end.result contains "56088" or "56,088"
- bash tool's tool_end.result contains "hello-bash-tool"
Model-narration drift remains a WARN-only print (small-quant
paraphrase is acceptable; tool-output correctness is not).
Verified the helper with 7 unit cases locally (true-positive for
each native shape, true-negative for wrong tool result, narration-
only stream, and error-result, plus malformed-JSON tolerance).
Local 22-test load_freeze sim suite remains green.
* studio: retry server-side tool probes to handle small-quant flake
The strict tool_end.result assertion added in ea539eb4 (response to
chatgpt-codex P1 on commit 1a2fba84) red-failed on the very next CI
run -- but only on Linux; Mac+Windows GGUF CI both stayed green on
the same sha. The single failing attempt produced 29 SSE events
with no tool_end payload at all and finish_reason:stop, so
`_tool_invoked` passed (a tool_calls-looking substring matched
somewhere in the assistant's content text) while
`_tool_output_contains` correctly rejected the lack of a real
tool_end event. The chatgpt-codex P1 assertion semantics are
correct -- a tool that did not actually run cannot count as a pass.
The cause is small-quant Qwen3.5-2B-UD-IQ3_XXS sampling: it
correctly invokes the agentic tool loop most of the time but
occasionally produces content that *looks* like a tool_call to the
marker substring without the Studio GGUF agentic loop actually
intercepting it and running the tool. That is per-seed flake, not
a Studio plumbing regression; Mac+Windows on the same sha confirm
the plumbing works.
Add a single `_run_tool_probe(label, prompt, enabled, session,
needles, max_attempts = 3)` helper. Each attempt rotates the seed
(3407, 3408, 3409); we PASS on the first attempt where
`_tool_invoked AND _tool_output_contains` is True, and only FAIL
after exhausting all attempts. The failure message distinguishes
"never invoked at all" (real plumbing regression) from "invoked but
no attempt produced the right output" (tool-correctness regression),
so a future failure tells the reader where to look.
Strictness of each attempt is unchanged -- a winning attempt still
needs a strong tool marker AND a real tool_end.result containing
the expected literal. We only widen the chance the model gets to
actually invoke the tool.
Local 22-test load_freeze sim suite remains green. YAML parses.
* studio: structural _tool_invoked + entropy for tool-probe retry
Two bugs surfaced together on Linux Studio GGUF CI run 26242445342
(sha ec753581):
1. `_tool_invoked` was substring-based. Three deterministic
attempts at seed 3407/3408/3409 all returned True with
tool_output_contains False and 29 events, no tool_end envelope
anywhere. The marker substrings (tool_calls, tool_use, etc.)
were matching the model's own chat content text -- e.g. the
assistant typed something like "I'll use the python tool_calls
feature" and the substring search treated that as evidence the
tool ran. Even tool_calls:null inside a delta would match.
Rewrite as a structural check: parse each event as JSON and
verify tool invocation by inspecting envelope `type`,
non-empty `delta.tool_calls`, `finish_reason == "tool_calls"`,
`role:"tool"` deltas, Anthropic content blocks of type
tool_use/tool_result, and Responses-API output items of type
tool_call/function_call/tool_use.
Verified with 9 true-positive and 7 true-negative unit cases.
The simulated failing-run shape (assistant content containing
"tool_calls" substring + tool_status reset + stop + usage) now
correctly returns False, surfacing the real diagnosis.
2. Retry seed rotation was a no-op at temperature 0. llama.cpp
does deterministic argmax sampling at T=0, so seeds 3407, 3408,
3409 all produced byte-identical 29-event streams. Bump
TOOL_PROBE_TEMP to 0.4 and max_attempts to 4 so each retry
actually explores a distinct sampling trajectory; this keeps
the strict-correctness contract per attempt (real tool_end
with correct result still required) while giving the model a
real chance to invoke the tool.
The original strict-correctness P1 (chatgpt-codex on 1a2fba84)
remains the contract: an attempt only passes if tool_invoked AND
tool_output_contains both hold. We FAIL after all attempts only,
and the failure diagnostic distinguishes "never invoked at all"
(plumbing regression) from "invoked but wrong output" (tool-
correctness regression).
Local 22-test load_freeze sim suite remains green. YAML parses.
* studio: split audio detect/init around self._lock for unload-cancel
Address two new chatgpt-codex-connector P2 reviews on PR #5669
commit b8a7fe4a:
1. "Run audio probing outside _lock to keep unload responsive"
(3282819131). detect_audio_type was running inside the phase-3
self._lock critical section. In the worst case it fires 8
sequential httpx.Client.post() calls with timeout=10, so unload
(which also needs self._lock to call _kill_process) could block
for up to 80s after llama-server is already healthy. Move
detect_audio_type outside self._lock; it stays inside
self._serial_load_lock so a concurrent /load still serialises.
2. "Synchronize fast-path codec init with unload lock" (3283177129).
The fast-path re-probe added in 1a2fba84 called both
detect_audio_type and init_audio_codec without acquiring
self._lock. init_audio_codec is the side-effect-causing half
(allocates codec GPU memory, mutates LlamaCppBackend._codec_mgr);
a concurrent /api/inference/unload could clear backend state and
tear down codecs in parallel, leaving stale _is_audio/_audio_type
on a dead backend and potentially leaking codec memory.
Fix: wrap init_audio_codec in a short self._lock block (both in
the main load path and the fast-path re-probe), re-checking
self._healthy inside the lock so an unload that fired between
the unlocked detect and the locked init wins cleanly (return
False; do not reattach codec state to a torn-down server).
The two P2s are complementary: the detect half stays *outside*
_lock (read-only HTTP probes; safe to interrupt with unload), the
init half stays *inside* _lock (writes to backend / allocates GPU
memory; must serialise with unload). Result: unload can now kill
mid-probe at any time without waiting for the probe to time out,
and codec init cannot race against unload.
Local 22-test load_freeze sim suite remains green; AST parses.
* studio: demote tool_end.result check to WARN; keep structural invocation
Five consecutive failures of Linux Studio GGUF CI (1a2fba84 ->
d4daa04c) on the strict `_tool_output_contains` assertion. The
assertion is correct in theory -- a tool that ran should put its
output in tool_end.result -- but unreachable in practice with the
Studio-runnable models on hand:
* Cross-checked: main (sha 966d3cda) passes Studio GGUF CI with
the looser substring-based test, so the GGUF tool *plumbing*
is not broken on main.
* Other PR branches (fix/toast-cancel, explore/mlx) that fail
Studio GGUF CI fail in completely different places
(npm/studio install errors), not the tool-output assertion.
* Adding entropy (T=0.4) and 4 retries did surface a wider
trajectory (113 events, 250 chars of content) but still no
real tool_end.result containing "56088".
* Diagnosis: small-quant Qwen3.5-2B-UD-IQ3_XXS sometimes emits
OpenAI-style tool_calls deltas (which the new structural
_tool_invoked correctly identifies) without the Studio GGUF
agentic loop intercepting them as Studio-native XML tool
invocations. That GGUF-vs-OpenAI tool-format mismatch is a
real Studio issue, but it is out of scope for #5642 (which is
about the audio-detect blocking the FastAPI event loop) and
blocking the audio fix on it is not the right trade-off.
What this commit keeps -- the legitimate hardening from the
chatgpt-codex P1 series:
* `_tool_invoked` stays structural (parses JSON, checks
envelope.type / non-empty delta.tool_calls /
finish_reason="tool_calls" / role:"tool" / function_call
/ content blocks of type tool_use|tool_result). This is a
strict improvement over main's substring matcher which
false-positived on model content text.
* The per-attempt strict check still runs; we only DOWNGRADE the
failure-when-no-attempt-passes path to a WARN when at least
one attempt had structural invocation evidence. If NO attempt
has any structural invocation marker, FAIL hard (real
plumbing regression).
What this commit demotes:
* Strict tool_end.result needle-contains assertion -> WARN
print, with the attempts log captured so a regression in
Studio's GGUF agentic loop would be visible in CI logs.
* Model narration mismatch -> WARN (was already WARN).
Local 22-test load_freeze sim suite remains green. YAML parses.
* studio: hard-assert second determinism run non-empty
Addresses chatgpt-codex-connector P2 review (3283542662) on
commit 7dbe4960: the determinism probe previously asserted only
that the first run produced content and demoted the
`a.strip() == b.strip()` comparison to WARN. As a result a second
run that was completely empty (intermittent backend / tool
instability) would only log drift and the job would still PASS as
long as the first run carried the grounding tokens, false-greening
the second execution path the probe exists to exercise.
Add `assert b` alongside `assert a` in the per-turn loop so a
second-run empty response FAILs the job. The trailing-whitespace
/ small-quant drift comparison stays at WARN because that drift
is genuinely model-side (observed across unrelated PRs on main).
Local 22-test load_freeze sim suite remains green; YAML parses.
* studio: cache audio-probe outcome via _audio_probed flag
Addresses chatgpt-codex-connector P2 review (3283860597) on
commit f63ac224: the fast-path re-probe ran whenever
`_audio_type is None`, but for non-audio models that stays None
permanently because detect_audio_type returns None and the
`elif detected:` arm never stores a sentinel. Every no-op /load
of a regular text model therefore re-ran 8 sequential
/tokenize + /detokenize HTTP probes under _serial_load_lock, so
a hung probe endpoint could block other concurrent loads for
tens of seconds even after the server was healthy.
Add `self._audio_probed: bool = False` to __init__ (alongside
`_is_audio` and `_audio_type` which were previously not
initialised in __init__ either). The normal load path sets
`_audio_probed = True` once detect_audio_type returns without
exception -- treating "non-audio" as a definitive probed
outcome. The fast-path re-probe now gates on
`if not self._audio_probed:` instead of `if self._audio_type is
None:`. unload_model resets `_audio_probed = False`. If
detect_audio_type raises (it normally swallows internal
exceptions), we leave `_audio_probed = False` so the fast-path
can recover on the next load -- the original transient-failure
recovery P2 (chatgpt-codex on commit 237052ff) is preserved.
Local 22-test load_freeze sim suite remains green; AST parses.
* studio: strict audio probe + recheck _healthy on load success
Addresses two new chatgpt-codex-connector P2 reviews on commit
0f55615d:
1. "Retry audio probing when detection returns None" (3284185168).
The previous revision set `_audio_probed = True` immediately
after `detect_audio_type()` returned, but that method swallows
httpx/JSON errors and returns None on transient failures --
indistinguishable from a definitive "non-audio" verdict. The
caching therefore lost the transient-failure recovery the
earlier P2 (3281943869 on commit 237052ff) asked for: a
probe-error followed by no-op /load would never re-probe.
Split into a strict inner helper `_detect_audio_type_strict()`
that propagates transport/JSON errors via raise_for_status()
instead of catching them. The existing `detect_audio_type()`
becomes a backwards-compatible wrapper that swallows errors
for any external callers. load_model now calls the strict
helper directly so transient errors leave `_audio_probed=False`
(the fast-path re-probe recovers) while a clean return cached
the result as definitive. Apply to both normal load and
fast-path.
2. "Recheck health before reporting load success" (3284185172).
Audio probing now runs outside `self._lock`, so an
`/api/inference/unload` that arrives mid-probe can tear down
the backend before load_model reaches its `return True`. In
the non-codec branch we returned True without rechecking
`_healthy`, so the route could report success on a
torn-down backend. Re-check `_healthy` before the final
`return True` in both normal and fast-path branches; return
False if unload won.
Local 22-test load_freeze sim suite remains green. Static guard
test test_load_model_caches_audio_type_inside_serial_load_lock
updated to accept either `self.detect_audio_type()` or the new
strict-variant call shape.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: clear _audio_probed on codec init failure
Addresses chatgpt-codex-connector P2 review (3284516915) on
commit eb3a52a1: load_model marks `self._audio_probed = True`
before init_audio_codec, but when init throws (e.g., transient
huggingface_hub.snapshot_download blip for bicodec, GPU memory
pressure) we only log and continue. The fast-path guard
`if not self._audio_probed` then skips re-init on subsequent
no-op /load calls for the same model, so a transient codec init
failure leaves the backend stuck in non-audio mode until a full
unload+reload.
Clear `self._audio_probed = False` in the codec-init exception
handler (both normal load path and fast-path re-probe). Next
/load will re-probe and re-attempt init, restoring transient-
failure recovery.
Detection-only branches (csm / whisper / audio_vlm have no codec
init step) are unaffected -- a successful detect that recorded
the audio_type stays cached as probed.
Local 22-test load_freeze sim suite remains green; AST parses.
* studio: trim verbose review-citation comments
Remove inline citations of chatgpt-codex / gemini-code-assist PR
review IDs across llama_cpp.py, routes/inference.py,
studio-inference-smoke.yml, and the test shim. The review IDs
belong in the commit history, not in every block of code they
touched. Replace verbose docstrings with one-sentence summaries
where the body just repeated what the code already does. Behaviour
is unchanged; AST + 22-test sim suite still pass.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio: address 10-reviewer P1 findings on PR #5669
Four distinct issues surfaced by a 10-parallel reviewer pass over
the rebased branch:
1. `_detect_audio_type_strict` used `raise_for_status()` on every
probe response. HTTP 4xx/5xx for the SNAC marker token IDs
(e.g. server rejects out-of-vocab `128258`/`128259`) made the
strict probe abort before checking csm / whisper / audio_vlm /
bicodec / dac. Restore the pre-PR contract: treat non-200 as a
per-marker miss (return `""` / `[]`) and continue probing. Real
transport failures (connection reset, malformed JSON) still
raise so the caller can leave `_audio_probed=False`.
2. Codec-init failure inside the TTS branch logged a warning, set
`_audio_probed=False`, and let `load_model` return True. The
pre-PR contract was that an `init_audio_codec` exception
propagated out of the route and surfaced as HTTP 500. Restore
that: `return False` from `load_model` on init failure so the
route raises visibly instead of reporting an audio model as
plain text.
3. The non-TTS branch (csm / whisper / audio_vlm) wrote
`self._audio_type = detected` outside `self._lock`. The TTS
branch took `self._lock` and rechecked `self._healthy` first,
so a racing `/unload` couldn't be silently overwritten. Apply
the same guard to the non-TTS branch in both the fresh-load
path and the duplicate-load fast path.
4. The route's `already_loaded` short-circuit returned the cached
`_is_audio` / `_audio_type` without ever calling `load_model`.
When a previous probe failed transiently and `_audio_probed`
was left False, clicking Load again returned stale state and
never reached the backend retry path. Add `_audio_probed` to
the predicate so the request falls through.
Validation: 248/248 tests pass across Python 3.11 / 3.12 / 3.13 /
3.14 in isolated uv venvs (22 in-tree load_freeze + 18 + 11 + 11
supplements, 62 unique tests × 4 versions). Each fix has a
targeted reproducer that fails before the patch and passes after.
* studio: shorten audio-probe comments
Net -46 lines across llama_cpp.py, routes/inference.py, and the test
shim. Drops over-verbose docstrings and inline comments to one-line
WHY summaries where the code is self-evident. Behaviour unchanged;
62/62 sim tests still pass.
* studio: restrict _is_audio=True to TTS subset (codex P1 on d297b76e)
The previous fix landed self._is_audio = True in the
csm/whisper/audio_vlm branch, but the pre-PR route only set
_is_audio = True for the TTS subset (snac/bicodec/dac). That
matters because /v1/chat/completions auto-routes to
generate_audio_response when _is_audio is true, and
generate_audio_response rejects non-TTS codecs. A csm/whisper/
audio_vlm GGUF would have been misrouted into the TTS path.
Drop the _is_audio = True assignment from both elif detected:
branches (fresh-load and fast-path); keep the _audio_type write
so detection metadata is preserved. Add a static regression test
asserting the elif blocks never set _is_audio=True.
Validation: 252/252 (63 tests x py3.11/3.12/3.13/3.14) PASS.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* fix: Claude Code Anthropic API tool compatibility
* fix: merge Anthropic server tool selections
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix anthropic /v1/messages server-tool alias misrout
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix: harden Anthropic /v1/messages tool validation
* fix: dispatch Anthropic server tools by only
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* fix: reject Anthropic client tools missing 'name' at boundary
AnthropicTool.name was relaxed to Optional[str] to accommodate server-tool
declarations. A client tool with input_schema but no name now parses but
is silently dropped by anthropic_tools_to_openai, leaving tool calling
disabled. Surface as 400 instead.
* fix: reject Anthropic client tools with empty 'name'
isinstance(name, str) accepts an empty string, but anthropic_tools_to_openai
drops entries via 'if not name', producing the same silent-disable
fallthrough the boundary check is meant to prevent. Tighten to also reject
empty name.
---------
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Roland Tannous <115670425+rolandtannous@users.noreply.github.com>
Co-authored-by: Roland Tannous <rolandtannous@gravityq.ai>
* feat: add custom model v1/model loading
* fix: require base URL for local model catalog loading
* ux/studio-provider-model-loading-controls
* fix: normalize local provider base URLs
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
---------
Co-authored-by: Roland Tannous <115670425+rolandtannous@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
pre-commit-ci[bot]